# Auto B-Roll
Source: https://docs.premierecopilot.com/features/auto-broll
Transcribes your timeline and places your own b-roll where it illustrates what is being said.
Auto B-Roll listens to your edit, looks at every b-roll clip in a folder of your project, and places them on a track above your timeline — wherever the visuals illustrate what's being said.
It uses **your own footage**. Nothing is generated, nothing is downloaded from a stock library.
Works in **Premiere Pro** and **DaVinci Resolve**.
## Quick Start
Put the clips you want available into a project bin. Only bins that actually contain video show up in the picker.
Open the **Tools Menu** and select **Auto B-Roll**.
Choose it in the dropdown — the field pulses green until you do, because nothing can run without it.
**B-roll / min** decides how much b-roll lands on your edit.
e.g. *"only nature shots, keep it subtle"*.
Click **Add Auto B-Roll** and let it work through its four steps.
Your timeline must be under **2 hours** — it gets transcribed, and beyond that the audio export becomes unreliable.
## Settings
| Setting | Range | What it does |
| ----------------- | ------------------ | ----------------------------- |
| **Mode** | Project / Timeline | Where your b-roll comes from. |
| **B-roll folder** | your project bins | The pool of clips it can use. |
| **B-roll / min** | 1–60 | Density target. |
| **Brief** | free text | Creative direction. |
### Mode
Pick a project bin full of b-roll. The clips are **added on a new track above your edit**. This is the mode to use.
Your b-roll already sits on a video track and gets **moved** to the spots where it fits. Coming soon — currently locked.
### B-roll / min
The target is your **timeline duration × this rate**, with a small tolerance. Density is treated as the priority: the AI aims to hit that count rather than holding out for a perfect visual every time.
* **2–4** — occasional punctuation. Interviews, corporate, talking-head where the face carries the video.
* **5–10** — the standard illustrated-video rhythm. **Start around 8.**
* **12+** — dense, fast-cut, montage-heavy. Needs a large, varied b-roll pool to avoid repetition.
Density above what your folder can support forces repetition. A rate of 15/min on a 10-minute timeline asks for \~150 placements — with 20 clips available, you'll see each one many times.
## How it matches
The run goes through four visible steps: **transcribe the timeline → read and analyze your b-roll → AI matching → place the clips.**
What matters for your results:
* **Matching is thematic, not literal.** A clip qualifies if it's figurative, evocative or simply related in mood, setting or subject. A city at dusk over a line about ambition is considered a good match, not a mistake.
* **Repetition is minimised, not banned.** Clips that haven't been used yet are strongly preferred; a clip comes back only when nothing fresh fits.
* **Several clips can stack on one long passage**, up to a small maximum — never on a short one.
* **Placements never overlap.** A clip that would run into the next one is shortened, not dropped.
* **A clip is never stretched beyond its own length.** Short source clips produce short placements.
Your b-roll only needs to be described **once**. Clips already analysed in a previous run are recognised, so re-running — or running on another sequence in the same project — is faster.
## Writing a Good Brief
The brief steers the creative direction. It's optional, and short is better.
### What works
* **Restrict the pool:** *"Only nature and landscape shots — skip anything with people."*
* **Set the tone:** *"Keep it subtle and atmospheric."* / *"Punchy, energetic, on-the-nose."*
* **Guide the interpretation:** *"Favour metaphorical matches over literal ones."* / *"Stay literal — show exactly what I'm talking about."*
* **Protect passages:** *"No b-roll over the intro or the call to action."*
* **Give context:** *"This is a product demo — prefer the office and workshop shots for the process parts."*
### What doesn't work
* **How much b-roll to place** — that's the B-roll / min setting.
* **Timecodes or exact placements** — *"put the drone shot at 2:15"*. The AI picks the moments; do a specific placement by hand.
* **Naming a file** — it works from what the clips *look like*, not from filenames.
* **Effects, transitions or speed** — placement only. No fades, no scaling, no reframing.
* **Asking for footage you don't have** — it can only use what's in the folder you picked.
### Recommended pattern
> *"\[What to include or exclude]. \[Tone]. \[How literal to be]. \[What to leave alone]."*
**Example:**
> *"Only exterior and nature shots, no faces. Calm and atmospheric. Prefer evocative matches over literal ones. Leave the first 20 seconds clean."*
If the results feel repetitive, the fix is usually **more clips in the folder** or **a lower density** — rarely a longer brief.
## Presets
The preset bar saves your working configuration, including the mode, folder, track, density, and brief. Build one per format so a recurring series is a two-click job.
## After the run
The b-roll lands on a track above your edit as ordinary clips: move, trim, replace or delete anything you disagree with. The underlying edit is untouched.
Review it as a pass, not clip by clip: play the timeline once and only stop on placements that actively distract. Auto B-Roll is there to give you a full first layer to prune, which is far faster than building one from scratch.
## Common Pitfalls
* **No folder selected** → the Start button stays disabled and the picker pulses. It's the only blocker you can clear yourself.
* **Empty bins don't appear** in the picker — only bins containing video are listed.
* **Timeline over 2 hours** → refused before anything runs.
* **A tiny b-roll folder with a high density** → heavy repetition. Add clips or lower the rate.
* **Very short source clips** produce very short placements — that's the source length, not a bug.
* **Touching the timeline while it's placing** → let the progress modal finish; it's writing to your sequence.
* **Music or noisy audio under the voice** hurts the transcription, and a weak transcript means weak matches.
**Recommended workflow:** a well-stocked, varied bin → 8 b-roll/min → a one-line brief → run → prune in one playback pass.
# Auto Color
Source: https://docs.premierecopilot.com/features/auto-color
AI colorist grade of your timeline — exposure, white balance, contrast and a cinematic look, with shots of the same scene matched to each other.
Auto Color grades your timeline like a colorist: it looks at an actual frame from every source clip, measures it, corrects the exposure and white balance, sculpts the contrast, and applies a look on top — while keeping shots from the same scene consistent with each other so your cuts don't jump.
Works in **Premiere Pro** and **DaVinci Resolve**.
## Quick Start
Shooting Log? Apply your **Log → Rec.709 conversion** (LUT or color-space transform) **before** running. Auto Color grades on top of your base image.
Open the **Tools Menu** and select **Auto Color**.
Type your instruction in the **prompt box** — e.g. *"warm cinematic look, match all the clips"*. Optional, but this is where the creative direction lives.
Leave **Time Start** and **Time End** empty to grade the whole timeline.
Click **Start Auto Color**.
**Log / flat footage without a conversion will not grade well.** Auto Color reads the image it is given: if you hand it a washed-out Log frame, it corrects a washed-out Log frame. Put your LUT or color-space transform on first.
## What it actually does
Every source is fingerprinted, then shots that belong to the same scene, lighting setup or camera are grouped so they share one consistent look. Unrelated scenes are deliberately **not** matched — a daylight exterior and a tungsten interior stay separate.
Each source is then graded individually: correction first (exposure, white balance, contrast), creative look second — following its group's shared direction when it has one.
### What gets adjusted
The grade is a full **Basic Correction** pass, not a two-slider nudge:
| Control | What it's used for |
| ------------------------ | ------------------------------------------------------------------------------------------ |
| **Exposure** | Bring the image to a balanced brightness. |
| **Temperature / Tint** | Neutralise the measured color cast — or push it for the look. |
| **Contrast** | Add shape, especially on flat footage. |
| **Blacks / Whites** | Set the black and white points — this is what makes an image feel filmic instead of milky. |
| **Shadows / Highlights** | Open crushed shadows, recover blown highlights. |
| **Saturation** | Punch or mute, with skin tones protected. |
**One frame per source is analysed**, not one per clip. If the same source appears eight times in your edit, it's analysed once and the grade is applied to all eight instances — consistently, and for the cost of one.
### How it lands on your timeline
| Host | Where the grade goes |
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------ |
| **Premiere Pro** | On **adjustment layers** placed on an empty video track above your clips — fully non-destructive. Your original clips are untouched. |
| **DaVinci Resolve** | Applied per clip on the first node. |
In Premiere, hide or delete the adjustment-layer track to see the before/after instantly — and to throw the whole grade away in one move.
## Settings
| Setting | What it does |
| ------------------ | ----------------------------------------------------- |
| **Prompt box** | Free-text creative direction. Overrides the defaults. |
| **Time Start (s)** | Only grade clips at or after this time. |
| **Time End (s)** | Only grade clips up to this time. |
Unlike Auto Mix, the time range here scopes **both the analysis and the grade** — only the clips in the window are looked at. Grading a section on its own means it won't be matched against shots outside the window, so expect it to sit slightly differently from the rest.
## Writing a Good Prompt
Describe the **image you want to see**. Reference a mood, a film, a palette — not slider values.
### What works
* **A look:** *"Warm cinematic look, teal shadows, film-like contrast."* / *"Clean and neutral, corporate."* / *"Cold, desaturated, moody."*
* **A reference:** *"Nordic thriller palette."* / *"Sunny golden-hour vlog feel."* / *"Documentary — natural, no stylisation."*
* **Matching intent:** *"Make everything match, it's all one interview."* / *"Keep each location distinct, don't match across scenes."*
* **A known problem:** *"My footage is too warm under this lighting, neutralise it."* / *"The interior shots are underexposed."*
* **Restraint:** *"Correction only, no creative look."* / *"Subtle — don't push the saturation."*
* **Skin priority:** *"Talking head — skin tones are the priority, everything else is secondary."*
### What doesn't work
* **Slider values.** *"Set exposure to +0.4"* — say the image is dark instead.
* **Per-clip instructions.** *"Make the third shot cooler"* — grade the timeline, then adjust that clip by hand. It's already an editable Lumetri instance.
* **Timecodes in the prompt.** Use the Time Start / Time End fields.
* **Selective / secondary corrections.** No masks, no power windows, no "only change the sky" or "isolate the red jacket". This is a primary grade.
* **Split-toning by name.** *"Teal shadows, orange highlights"* is understood as a direction, but true wheel-based split-toning isn't part of what gets applied — expect the spirit, not the exact technique.
* **Fixing the shot.** Clipped highlights that hold no data, heavy noise, or a badly out-of-focus frame can't be recovered by a grade.
* **A LUT by name.** *"Apply Kodak 2383"* won't load a LUT. Describe the look and it will be approximated with the correction controls.
### Recommended pattern
> *"\[The look you want]. \[Matching intent]. \[Any known problem]. \[How far to push it]."*
**Example:**
> *"Warm, filmic look with deep blacks — golden-hour feel. All the interview shots are the same setup, match them. The B-roll outside is a bit cold, neutralise it. Keep it subtle, skin must stay natural."*
If the first pass overshoots, add one restraint sentence (*"much more subtle, correction-led"*) and re-run, rather than rewriting the whole brief.
## After the run
The grade is standard, editable color correction — nothing is baked in. You can retune any shot, copy a grade from one clip to another, or delete it entirely.
Review on your cuts, not clip by clip. A grade that looks great in isolation but jumps at a cut is the real failure mode — and it usually means two shots that should have been matched weren't. Say so in the prompt and re-run.
## Common Pitfalls
* **Log footage with no conversion applied** → the most common cause of a disappointing result. Convert first.
* **An already-graded timeline** → Auto Color adds its own correction on top of yours. Remove your existing grade first, or the two stack.
* **Nested sequences** → the clips inside can't be analysed as separate sources. Flatten first.
* **Expecting scene-to-scene uniformity** → grouping is deliberately conservative. Different lighting setups stay different unless you explicitly ask to match everything.
* **A very large timeline** costs proportionally more: the price scales with the number of **unique sources**, not the number of clips or the duration.
* **Frames that can't be exported** (footage offline, media on a blocked or synced folder) are skipped — check your media is online before running.
**Recommended workflow:** convert Log → one full pass with a short look-and-matching prompt → review at the cuts → re-run with a restraint or matching correction if needed → hand-tune the two or three shots that still stand out.
# Auto Mix
Source: https://docs.premierecopilot.com/features/auto-mix
AI sound-engineer mix of your whole timeline — levels, EQ, compression, de-noise and music ducking under the voice.
Auto Mix listens to every audio clip in your sequence and mixes it like a sound engineer would: it sets each source to a proper loudness target, cleans up the voice, leaves the music alone but puts it at the right level, and rides the music down under every line of dialogue.
Everything is applied as **real, editable effects** on your clips — nothing is baked in.
Auto Mix is a **Premiere Pro** feature. It is not available in DaVinci Resolve.
## Quick Start
Open the **Tools Menu** and select **Auto Mix**.
Type your instruction in the **prompt box** at the bottom of the panel — e.g. *"clean podcast mix, keep the music well under the dialogue"*. Optional, but this is where most of the control lives.
Leave **Time Start** and **Time End** empty to mix the whole timeline.
Click **Start Auto Mix**. Count roughly **one minute per hour of timeline**.
## What it actually does
Auto Mix works in two passes, and knowing the difference explains most of the results.
Each source clip is identified as **speech**, **music** or **SFX**, then given its own treatment: level, high-pass, compression, de-noise, de-ess, limiter — only what that clip actually needs.
Wherever a music or SFX bed overlaps speech, a smooth **volume automation** is written on the bed: it dips before the line starts, holds under it, and comes back up after.
### Level targets
Levels are set relative to a delivery standard, with the **voice as the anchor** and everything else placed below it:
| Delivery | Speech anchor |
| -------------------------------- | ------------- |
| **Podcast / voice** (default) | -16 LUFS |
| **YouTube / streaming / social** | -14 LUFS |
| **Broadcast / TV / EBU R128** | -23 LUFS |
Music sits clearly below the voice and is ducked further under it; SFX land in between.
Just name your platform in the prompt — *"master for YouTube"*, *"broadcast delivery"* — and the whole mix re-anchors around it. That single word does more than any manual gain pass.
### Processing philosophy
* **Voice gets the work.** High-pass to remove rumble, compression only when the delivery is genuinely uneven, de-noise only when there's a real noise floor, de-essing only when it's actually sibilant.
* **Music is left alone.** A music bed is already produced and mastered, so it gets a **level and nothing else** — no EQ, no compression. Only its volume moves.
* **SFX stay minimal.** Level, and a limiter if a peak demands it.
Nothing is applied "just in case". If your voice track is clean and even, you'll get a gain change and a high-pass, and that's it — that's the correct mix, not a missing one.
## Settings
| Setting | What it does |
| ------------------ | -------------------------------------------------- |
| **Prompt box** | Free-text instruction. Overrides the defaults. |
| **Time Start (s)** | Apply the mix only to clips at or after this time. |
| **Time End (s)** | Apply the mix only to clips up to this time. |
**The time range limits where the mix is applied, not what is analysed.** The analysis always reads the whole timeline, so a range still gets levels consistent with the rest of your sequence. This is deliberate — mixing a 30-second window in isolation would make it jump against its neighbours.
Use the range to fix one problematic section after a first full pass, rather than re-mixing everything.
## Writing a Good Prompt
The prompt is optional, but it's how you set intent. Describe the **result you want to hear**, not the parameters.
### What works
* **The delivery target:** *"Master for YouTube."* / *"Broadcast delivery, EBU R128."*
* **The music/voice balance:** *"Keep the music very low under the dialogue, it should barely be there."* / *"The music can stay present between the lines."*
* **The overall character:** *"Clean, neutral podcast mix."* / *"Punchy and loud, energetic edit."* / *"Natural and dynamic, don't squash it."*
* **A known problem with the recording:** *"There's air conditioning in the background, clean it up."* / *"I'm sibilant, tame the S sounds."* / *"My delivery goes from whisper to shout, even it out."*
* **What to protect:** *"Don't touch the music, only fix the voice."* / *"Don't over-compress, keep the dynamics."*
* **Ducking behaviour:** *"Duck the music hard under every line."* / *"Only light ducking, this is a music-led video."*
### What doesn't work
* **Per-clip instructions.** *"Lower the third clip by 3 dB"* is a local retouch — do it by hand, or ask the Copilot for that single clip. Auto Mix is a whole-timeline pass.
* **Timecodes.** *"Boost the intro at 0:15"* — use the Time Start / Time End fields instead.
* **Creative sound design.** No reverb, delay, pitch, telephone effect, or vocal character processing. This is a mix, not a design pass.
* **Fixing the recording itself.** De-noise reduces a noise floor; it doesn't remove a passing motorbike, a clipped peak or a room with bad acoustics.
* **Renaming or re-classifying a clip.** If a clip is misread as music, say so in words (*"the file called 'ambience' is dialogue"*) rather than expecting a setting.
* **Asking for a specific dB number per effect.** Say what you want to hear; the target does the rest.
### Recommended pattern
> *"\[Delivery target]. \[Voice/music balance]. \[Known problem to fix]. \[What to leave alone]."*
**Example:**
> *"Podcast mix for Spotify. Music clearly under the voice, ducked hard on every line. There's a constant hum in my mic — clean it. Don't over-compress, I want the delivery to breathe."*
If the first pass isn't right, change **one** thing in the prompt and re-run rather than rewriting the whole instruction — it's much easier to tell what moved.
## After the run
The mix arrives as standard Premiere audio effects on your clips — volume, high-pass, compressor, de-noise, de-esser, limiter — plus volume keyframes on the ducked beds.
That means you can:
* **Adjust anything by hand** in the Effect Controls panel.
* **Reshape a duck** by dragging its keyframes.
* **Remove a treatment** you disagree with, clip by clip.
* **Undo the whole thing** with Cmd/Ctrl+Z.
Listen on the monitoring you actually deliver on. A mix anchored at -16 LUFS is correct even if it feels quiet next to a loud reference track in another app.
## Common Pitfalls
* **All audio on one track** → clips still get treated individually, but a voice and a music bed sharing a track make classification harder. One source type per track gives the best result.
* **A music bed that never ducks** → it probably wasn't read as music. Say what it is in the prompt.
* **Nested sequences or multicam** → the audio inside them can't be analysed as separate sources. Flatten first.
* **Already-processed clips** → Auto Mix adds its own effects on top of yours. Remove your previous audio effects before running, or the two stack.
* **Expecting a repair tool** → de-noise handles a steady noise floor. Clipping, wind blasts and room reverb are recording problems it cannot undo.
* **Touching the timeline mid-run** → let it finish; it's reading and writing your sequence.
**Recommended workflow:** one source type per audio track → a two-sentence prompt naming your platform and the music/voice balance → full-timeline pass → listen → fix any single section with a Time Start / Time End re-run.
# Auto SFX
Source: https://docs.premierecopilot.com/features/auto-sfx
Analyze your edit, generate matching sound effects with AI, review every suggestion, and place them automatically on the timeline.
Auto SFX reads your edit, finds moments that can benefit from sound design, generates matching sound effects, and places them automatically on your timeline.
You stay in control: the tool first creates a list of suggestions, then lets you select, reject, or add sounds before anything is generated or placed.
Works in **Premiere Pro** and **DaVinci Resolve**.
## Video tutorial
Watch the complete Auto SFX workflow, from choosing the analysis settings to reviewing and placing the generated sounds:
[Watch the tutorial on YouTube](https://www.youtube.com/watch?v=_hnLQDwSen8)
## Quick Start
Open the **Tools Menu** and select **Auto SFX**.
Select **Whole timeline** to process the full sequence, or **In / Out** to limit the analysis and placement to your marked range.
Enable **Speech**, **Cuts**, or both. Then choose the sound categories the AI may use.
Adjust **Sound effects per minute**, select an AI model, and optionally describe the sound design you want in the **Brief** field.
Click **Start Analysis**. Auto SFX reads the selected range and proposes a timed list of sound effects.
Deselect unwanted suggestions, add any missing sound manually, then click **Generate & place**.
Keep Premiere Pro or DaVinci Resolve open and do not edit the timeline while Auto SFX is analyzing, generating, or placing sounds.
## Choose the range
| Range | What it does |
| ------------------ | ----------------------------------------------------------------------- |
| **Whole timeline** | Analyzes the sequence from beginning to end. |
| **In / Out** | Analyzes and places sounds only between the sequence In and Out points. |
The chosen range determines what is analyzed, where sounds may be placed, and the estimated credit cost.
If **In / Out** is selected but no valid In and Out points are set, Auto SFX uses the whole timeline and displays a warning.
## Triggers
Triggers decide which moments become candidates for sound design. At least one trigger must remain enabled.
Exports and transcribes the sequence audio. The AI reads what is being said and identifies phrases, ideas, reveals, numbers, and punchlines that may benefit from sound design.
Detects the start of each incoming shot and reads contact sheets made from timeline frames. This gives the AI visual context around edits, actions, objects, and transitions.
You can combine both triggers. This gives the AI the spoken context and the picture around each cut.
Use **Speech** for podcasts, talking heads, explainers, and interviews. Add **Cuts** when visual transitions and on-screen actions should also drive the sound design.
## Sound categories
Choose which families of sound the AI is allowed to propose. At least one category must remain enabled.
| Category | Best for |
| -------------- | ---------------------------------------------------------------------------------------------------------- |
| **Impact** | Hits, slams, thuds, booms, stingers, reveals, and emphasis. |
| **Transition** | Whooshes, swishes, pass-bys, reverses, risers, and downers around edits. |
| **Foley** | Concrete synchronized actions and details such as clicks, doors, footsteps, objects, and interface sounds. |
| **Ambience** | Continuous room tones, environments, drones, and atmospheric beds. Disabled by default. |
Several complementary categories can be layered at the same moment. Auto SFX will not place the same category twice on one candidate moment.
## Sound effects per minute
This slider sets a **target density**, from 1 to 20 sounds per minute. It is not a guarantee that every requested slot will be filled: Auto SFX prefers fewer relevant sounds over effects placed without enough context.
Sparse and discreet. Good for documentary, corporate, interviews, and long-form edits.
Intentional and balanced. The recommended starting range for most edits.
Dense and energetic. Better suited to Shorts, Reels, trailers, and fast edits.
When the **Cuts** trigger is enabled, the number of detected cuts can raise the number of candidate effects. A dense cut-heavy edit may therefore produce more suggestions than the rate alone implies.
## AI model
| Model | Best for |
| -------------------- | ------------------------------------------------------------- |
| **Gemini Flash 3.7** | The fastest option for straightforward picking. |
| **Gemini 3.1 Pro** | Better understanding of rhythm and longer context. |
| **Sonnet 5** | Balanced taste, context, and speed. |
| **Claude Opus 5** | The most deliberate sound-design choices for demanding edits. |
The model chooses the moments, category, duration, level, and generation prompt for every proposed sound. It does not generate the audio during analysis.
## Writing a good brief
The **Brief** is optional. Use it to describe the overall intent, sounds to favor or avoid, and moments that should remain quiet.
### What works
* **Style:** *“Subtle cinematic sound design, realistic and restrained.”*
* **Transitions:** *“Use soft whooshes only on major scene changes.”*
* **Emphasis:** *“Add clean impacts on important numbers and product reveals.”*
* **What to avoid:** *“No cartoon sounds, no risers, no ambience.”*
* **Selective direction:** *“Keep dialogue sections quiet and focus on visual actions.”*
### What does not work well
* Exact file names or requests to use a particular sound library.
* A long list of timecodes. Add those sounds manually during review instead.
* Vague instructions such as *“make it better”* without a style or editorial intention.
* Asking the tool to change the edit, mix the dialogue, or add music.
A short brief with one style, one priority, and one restriction usually gives the clearest result.
## Review before generation
After analysis, every proposal appears with:
* Its timeline timecode.
* The generation prompt describing the sound.
* Its category.
* A selection checkbox.
All proposed effects are selected by default. Deselect anything you do not want before clicking **Generate & place**.
### Add your own sound
If the AI missed a moment, use **Add your own**:
1. Enter the time in seconds.
2. Describe the sound in a few English words, for example *“dull wooden thud”*.
3. Click the **+** button.
Your sound is added chronologically to the review list and selected automatically. It uses the same generation and placement pipeline as AI suggestions.
## Generation and placement
When you click **Generate & place**:
1. The selected prompts are sent to the sound generator.
2. Identical sounds requested at several moments are generated only once and reused, which keeps the palette coherent and avoids duplicate generation costs.
3. Auto SFX creates enough audio tracks to prevent generated sounds from overlapping on the same track.
4. Each sound is placed just before its target moment so its attack lands correctly on the edit.
5. The level chosen during analysis is applied to the placed clip.
Generated sounds are real timeline clips. You can move, trim, mix, mute, or delete them after placement.
Review the result with dialogue and music enabled. Auto SFX sets a sensible starting level, but the final balance still depends on your complete mix.
## Credits
Auto SFX displays an estimate before analysis, but credits are charged **step by step for what actually runs**:
| Operation | Credit cost |
| -------------------- | ---------------------------------------------------------------------------------- |
| Speech transcription | 10 credits per hour, prorated, with a minimum of 1 credit when transcription runs. |
| Visual analysis | 1 credit per contact sheet of up to 6 frames. |
| Sound generation | 4 credits per unique generated sound. |
Analysis and generation are separate. You can review the proposed list before paying to generate its sounds. If the same generated sound is reused at several moments, it is charged only once.
The estimate may differ from the final charge. A stopped or partially failed run is charged only for the steps that were actually completed.
## Common pitfalls
* **No active sequence**: open the sequence you want to process, then refresh the range.
* **No valid In / Out range**: set both marks, or use Whole timeline.
* **No speech in the selected range**: disable Speech and use Cuts, or select a range containing spoken audio.
* **No video cuts detected**: disable Cuts, or check that the sequence contains video clips in the selected range.
* **Too many sounds**: lower Sound effects per minute, disable categories, or ask for restraint in the brief.
* **Sounds do not match the final mix**: adjust their clip gain after placement. Auto SFX cannot know the final loudness of every music and dialogue bus.
* **Editing during processing**: moving clips while the tool is reading or placing can invalidate its timecodes.
**Recommended starting point:** Whole timeline, Speech + Cuts, Impact + Transition + Foley, 4 to 6 sounds per minute, Gemini Flash for a first pass, and a one-sentence brief describing the desired restraint and style.
# AutoZoom
Source: https://docs.premierecopilot.com/features/auto-zoom
Automatically generate punch-ins and dynamic zooms on your timeline.
AutoZoom analyzes your sequence and places a series of zooms (punch-ins / outs) on your timeline automatically. It combines video cuts, speech, emotional peaks and AI context analysis to decide *where* and *how* to zoom.
## Quick Start
Open the **Tools Menu** (bottom left) and select **AutoZoom**.
Position the playhead anywhere inside the sequence you want to process.
Activate one or more **Triggers** (Cuts, Emotion, Speech, Random, Context) — see below.
Set the sliders (**Motion Camera**, **Zoom Rhythm**, **Zoom Fastness**, **Zoom %**) to match the feel you want.
Click **Start** — a backup of your sequence is created automatically before zooms are applied.
![AutoZoom interface]()
## Triggers
Each active trigger gets an equal share of the total number of zooms. Activating more triggers spreads zooms across more types of moments.
Places a zoom on every video cut in your sequence. **Free** — no transcription needed.
AI detects emotional peaks in speech (laughs, surprise, conviction). Requires transcription.
Places a zoom at the start of each spoken segment. Requires transcription.
Fills the longest gaps between zooms. **Free** — useful to keep rhythm steady.
AI reads the transcript and zooms on punchlines, topic changes, or anything you describe in the **text prompt**. Requires transcription.
Activating **Emotion**, **Speech** or **Context** triggers a **single shared transcription** — you are not charged multiple times.
## Intensity Sliders
| Slider | Range | What it does |
| ----------------- | ------- | --------------------------------------------------------------------- |
| **Motion Camera** | 0–4 | How much the camera moves during a zoom. At 0, zooms are static. |
| **Zoom Rhythm** | 1–5 | Density of zooms per minute (10/min at 1 → 30/min at 5). |
| **Zoom Fastness** | 1–5 | Duration of the zoom animation. Higher = snappier. |
| **Zoom (%)** | 100–300 | Maximum zoom amount. Each individual zoom uses 30–100% of this value. |
## Transition Style
Pick one or more transition types in **Box Settings**. At least one must stay active.
| Type | Feel |
| --------------- | --------------------------------------- |
| **Jump Cut** | Hard, instant snap to the zoomed frame. |
| **Ease In Out** | Smooth animated transition. |
| **Snap In Out** | Short, aggressive snap. |
You can enable **Sound In / Out** for each type to add a SFX (woosh / reverse) on every zoom.
## Interactive Preview
Click the refresh button to export the current Premiere frame as a preview.
**Drag** anywhere on the image to define the **center** of the zoom (where the camera will land).
**Drag the corners** of the green box to set how much the zoom crops in. The green box represents the area that will fill the screen after zoom.
## Writing a Good Text Prompt
The text prompt at the bottom of the extension is **only used if Context (AI) is active**. Otherwise it is ignored.
### What works
* **Target a type of information:** *"Zoom on every mention of numbers, statistics or results."*
* **Target a theme:** *"Zoom when I talk about personal experience or tell an anecdote."*
* **Target a subject:** *"Zoom whenever I mention a brand name or a product."*
* **Reinforce editorial beats:** *"Focus on punchlines and impactful sentence endings."*
* **Filter by energy:** *"Avoid calm moments — only zoom when I raise my voice."*
### What doesn't work
* Asking to change **intensity** or **speed** — these are controlled by sliders only.
* Asking for a specific **transition type** (jump / ease / snap) — chosen automatically.
* Asking for **spatial coordinates** — driven by the interactive preview only.
* Giving a **manual list of timecodes** — the AI picks moments freely.
### Recommended pattern
> *"Zoom on \[type of editorial moment] when \[narrative condition]. Avoid \[what you don't want]."*
**Example:**
> *"Zoom every time I announce a statistic or give an actionable tip. Avoid transitions and descriptive passages."*
## Common Pitfalls
* **No trigger active** → only cuts will be processed, which may produce zero zooms on a single-shot video.
* **No transition type active** → AutoZoom returns nothing. Keep at least one box type checked.
* **Transcription fails** → Emotion / Speech / Context are silently skipped. Only Cuts and Random will run.
For talking-head / podcast footage, start with **Speech + Context + Cuts**, Zoom Rhythm at 2–3, and a short text prompt describing the editorial intent.
# Claude Cut
Source: https://docs.premierecopilot.com/features/claude-cut
AI rough cut for talking-head footage: removes bad takes, repetitions and dead air, and lets you review every cut before applying.
Claude Cut turns a raw talking-head take into a clean rough cut. It transcribes your sequence, then an AI reads the whole transcript and decides which segments belong in the final video — dropping the mic checks, the retakes, the "wait, let me say that again", and the dead air between words.
You review everything as **editable text** before a single frame is touched. Nothing is applied until you click **Apply Cut**.
Works in **Premiere Pro** and **DaVinci Resolve**.
Claude Cut is built for **single-speaker footage**: YouTube monologues, founder explainers, video essays, course modules, interview answers. It is not a multicam or dialogue-scene tool.
## Quick Start
Open **Claude Cut** from the Tools Menu. Your sequence must be open, with at least one audio track carrying the voice.
Choose the AI model in the **Model** box (top left). Sonnet 5 is the default.
The green **Analyze** button runs the whole pipeline on its own: silence detection → transcription → AI analysis. Leave the app alone while the progress modal is up.
Segments the AI wants to remove are flagged **CUT** in red; the rest stay **KEEP** in green. Read them, flip whatever you disagree with.
Click **Apply Cut**. The cut clips are removed and the gaps closed, in one click.
While the progress modal is open, **keep Premiere Pro / DaVinci Resolve in the foreground and don't touch the timeline**. The pipeline is driving your sequence.
## Step 1 — Analyze
### Model
| Model | Best for |
| ------------------- | ---------------------------------------------------------------------------------------------------------- |
| **Sonnet 5** | The balanced default. Fast, reliable, good judgement on most footage. **Start here.** |
| **Claude Opus 4.8** | The most careful reader. Use it on dense, technical or high-stakes content where a wrong cut is expensive. |
| **Gemini 3.1 Pro** | Long-form. Useful on very long takes where the same idea comes back 20 minutes later. |
If a run over-cuts or misses obvious repetitions, **change the model and re-run** before hand-fixing dozens of segments. Different models make different judgement calls on the same take.
### Transcription precision
The small chevron button to the left of **Analyze** opens the engine menu:
Fast, reliable transcription. Included — no extra credits. The right choice in the vast majority of cases.
Re-syncs **every word** to the audio for sharper cut points. Slightly slower and costs extra credits (shown on the button).
Turn on **advanced word precision** when the cuts land a fraction of a second early or late — typically on fast speech, strong accents, or heavily overlapping delivery. On a calm, well-recorded take, standard is indistinguishable and cheaper.
### What the pipeline actually does
The single **Analyze** button chains three steps, shown live in the progress modal:
| Step | What happens |
| ---------------------- | ----------------------------------------------------------------------------------------- |
| **1. Detect silences** | Finds the dead air between words. Nothing is applied yet — the ranges are kept in memory. |
| **2. Transcribe** | Exports and transcribes your sequence audio. |
| **3. AI analysis** | The model reads the full transcript and marks what to remove. |
Both the silences and the AI's cuts are applied together, later, when you click **Apply Cut** — so the transcript you review always matches the timeline you're looking at.
The whole run is billed as **one combined charge**, and only if it completes. A failed or aborted run doesn't cost you.
## What the AI removes — and what it never touches
Understanding this is what makes the review step fast.
### It removes exactly two things
Mic checks, "is it rolling?", framing chatter, self-direction spoken out loud, asides to whoever is behind the camera, post-take reactions ("was that good?"). Almost always clustered at the **very start** and the **very end** of the take.
Retakes of the same line, verbatim repeats, and reformulation chains where the speaker searches for the right phrasing. **One version survives** — usually the most complete one — and the others go.
### It never does these
* **Rewrite, rephrase or reorder anything.** Your words stay in your order. The only lever is which segments survive.
* **Tighten for style.** A segment that is merely slow, long-winded or "could be punchier" is kept. That's an editing decision, not a cleanup one.
* **Cut a deliberate repetition.** Rhetorical triples ("It's not about speed. It's not about price. It's about trust.") and emphasis ("very, very fast") stay.
* **Drop new information**, even when it's clumsily phrased.
* **Break a seam.** Connector segments ("and that's why…", "but the thing is…") are kept when removing them would make the following line dangle.
The AI is deliberately **conservative**: keeping a slightly weak segment costs you almost nothing, while dropping a load-bearing one breaks the video. Expect it to leave in things you'd personally cut — that's the intended bias, and the review pass is where you tighten further.
## Step 2 — Review
This is not an optional step. Treat the AI output as a strong first pass, never as a final cut.
### Editing the transcript
| Action | Effect |
| ------------------------------- | ---------------------------------------------------------------------------------------- |
| **Click the KEEP / CUT chip** | Flips the whole segment. |
| **Click a word** | Toggles that single word — and moves the playhead there, so you can hear the exact spot. |
| **Double-click a word** | Toggles the whole clause around it (up to the nearest punctuation). |
| **Triple-click** | Toggles the entire segment. |
| **Click and drag across words** | Toggles the whole selection at once. |
| **Click a timecode** | Jumps the playhead to that segment. |
| **Reset button (top right)** | Brings everything back to KEEP. |
The **Timeline Metrics** box tracks the damage live: **Del.** is how much you're removing, **New Dur.** is what the sequence will last after applying.
Review in this order: (1) scan the **red** blocks at the start and end of the take — that's where pollution clusters and the AI is almost always right; (2) read the **green** lines immediately before and after each red block, out loud if you can — that's where a bad cut shows up; (3) only then hunt for extra fat to trim yourself.
## Step 3 — Apply Cut
**Apply Cut** disables the cut segments and immediately removes the disabled clips, closing the gaps — one click, clean timeline.
Listen back after applying. If a seam jumps, **undo** (Cmd/Ctrl+Z), flip that segment back to KEEP, and apply again. Don't re-run the whole analysis for a single bad seam.
## Steering the AI with a prompt
The **Analyze** button in the panel runs the default cleanup — there is no prompt box in the panel. To steer the AI, ask the **Copilot** in the chat instead:
> *"Clean up my sequence — remove the bad takes and repetitions, but keep every personal anecdote even if it's long."*
The Copilot runs the same engine, plus your instruction.
### What a steering prompt can do
* **Protect a category of content:** *"Keep every emotional anecdote and personal story, even the rambling ones."*
* **Protect a topic:** *"Never cut anything about pricing or the guarantee — I need those beats intact."*
* **Set the aggressiveness:** *"Be aggressive on the intro and the outro, conservative in the middle."*
* **Choose between duplicates:** *"When I say something twice, keep the first, more spontaneous version."* (The default keeps the most complete one.)
* **Handle a known habit:** *"I restart my sentences a lot — drop the false starts."*
* **Flag your workflow:** *"I always do three takes of each line back to back — keep the last one."*
### What a steering prompt cannot do
* **Rewrite or reorder.** No rephrasing, no moving a paragraph earlier, no adding a transition word to fix a seam.
* **Hit a target duration.** *"Cut it down to 5 minutes"* will not work — the AI removes what's removable, not a quota.
* **Cut by timecode.** *"Cut everything after 12:30"* is a timeline operation, not a cleanup one. Do it yourself, or ask the Copilot for a plain cut.
* **Judge delivery.** It reads the transcript, not the performance. It can't know which take had better energy, only which is more complete.
* **Cut for topic.** *"Remove the part about the competitor"* is an editorial decision outside its two rules — do it in the review pass, it's two clicks.
### Recommended pattern
> *"\[How aggressive]. Protect \[content you refuse to lose]. \[Any habit of yours worth knowing]."*
**Example:**
> *"Standard cleanup, slightly aggressive at the start. Protect anything where I give a number or a concrete example. I restart sentences often — keep the last attempt."*
Keep the prompt to **two or three sentences of intent**. Long, rule-heavy prompts don't produce a better cut — they mostly make the AI hesitant, and a hesitant pass keeps everything.
## Common Pitfalls
* **Several audio tracks with clips** → from the Copilot, the run stops and asks you to confirm first. Claude Cut is designed for a single voice track; on a multi-track timeline, check the result carefully.
* **Music or B-roll audio under the voice** → transcription quality drops and so does the cut. Mute those tracks before running.
* **Applying without reading** → the fastest way to a broken video. The AI over-cuts casual, vlog-style delivery and under-cuts subtle reformulations.
* **Very long takes** are processed in batches automatically: the analysis takes longer, the result is the same.
* **Nothing got cut** → that's a valid answer. On a clean, scripted take there may be nothing to remove.
* **Re-running Analyze** starts from scratch and discards your manual KEEP/CUT edits. Finish reviewing before you re-run.
**Recommended workflow:** Sonnet 5 + standard precision → Analyze → review start and end first → Apply Cut → listen back → fix seams with Cmd+Z and a toggle. Move to Opus 4.8 or advanced word precision only when the standard pass disappoints you on that specific footage.
# Gen AI
Source: https://docs.premierecopilot.com/features/gen-ai
Generate images, videos, and audio from text or reference media without leaving your editing workspace.
Gen AI brings image, video, and audio generation into Premiere Copilot. Describe what you want, optionally provide reference media, adjust the available settings, and save the result directly into your project workflow.
The available inputs and settings change automatically depending on the type of generation you select.
## Quick Start
Select **Image**, **Video**, or **Audio**.
Pick an option that supports the kind of result and inputs you need.
Describe the subject, action, style, framing, light, and mood as clearly as possible.
Upload a file or capture the required image, video, or audio directly from the active timeline.
Choose where completed generations should be downloaded.
Check the estimated price, launch the generation, and follow it in the history panel.
## Media categories
| Category | Typical uses |
| --------- | ---------------------------------------------------------------------------------------------- |
| **Image** | Stills, backgrounds, illustrations, product visuals, variations, and edits of existing images. |
| **Video** | Text-to-video, image animation, shot extension, transformations, and short generated inserts. |
| **Audio** | Sound effects, speech, music, and other generated audio when supported by the selected option. |
## Reference media
Some generations work from text alone. Others require one or more reference files. The interface displays only the inputs that are relevant to the selected option.
You can:
* Browse for a local image, video, or audio file.
* Capture the current timeline frame for an image input.
* Export a short timeline section when a video reference is required.
* Export the selected audio when an audio reference is required.
* Provide several reference images when the option supports a list.
Place the playhead on the cleanest representative frame before using timeline capture. Avoid frames with motion blur, transitions, or temporary overlays.
## Writing a useful prompt
Describe the visible or audible result, not the process:
* **Image:** *“Studio product photograph of a black camera on brushed steel, soft side light, dark neutral background.”*
* **Video:** *“Slow push-in toward the cabin, light snow moving across frame, stable cinematic camera, dusk.”*
* **Audio:** *“Short dry mechanical camera shutter, close and detailed, no ambience or voice.”*
For edits, say what must change and what must remain untouched. For animation, describe both the movement of the subject and the movement of the camera.
## Dynamic settings
Settings vary by generation and can include aspect ratio, output size, duration, number of results, strength, seed, or other controls. Hover over a setting when a description is available.
A higher duration, resolution, or number of results can increase the estimated price and processing time. Check the estimate again after changing settings.
## History and files
Every request appears in the history with its prompt and progress. Completed results are downloaded to the selected output folder. Failed items keep their error message so you can adjust the inputs and try again.
Pin frequently used generation options to keep them easy to find.
## Common pitfalls
* **A required input is empty**: add every reference field shown by the interface.
* **The captured frame is wrong**: move the playhead, then capture it again.
* **A local file was moved during processing**: keep source files in place until the request finishes.
* **The output folder is unavailable**: select a local writable folder.
* **A vague prompt** produces generic results. Describe subject, action, framing, light, and restrictions.
* **Reference media and prompt conflict**: state clearly which elements of the reference must be preserved.
Start with one clear result and modest settings. Once the composition or motion is right, increase quality or duration for the final generation.
# Jump Cut Tool
Source: https://docs.premierecopilot.com/features/jump-cut
Automatically remove silence from your footage.
Jump Cut removes silence from your footage automatically. It uses **voice detection** — not a simple volume threshold — so it keeps whispers, breaths at the end of a sentence and quiet delivery, while cutting real dead air. It is approximately **10x faster** than competitors like AutoPod.
Works in **Premiere Pro** and **DaVinci Resolve**.
## Quick Start
The panel is organised in three numbered steps: **Settings → Preview → Apply to timeline**.
Open the **Tools Menu** (bottom left) and select **Jump Cut**.
Put the playhead over a representative part of your sequence — one containing both speech and silence.
Click **Preview**. A 15-second sample is analysed and drawn as a waveform: everything shaded **red** will be removed.
Move the sliders and watch the red zones update **instantly** — no re-analysis needed. Press play to listen to the sample.
Click **Create Jump Cuts**. Your sequence is backed up automatically before anything is cut.
![Jump Cut Interface]()
## Step 1 — Settings
| Setting | Range | Default | What it does |
| ------------------------ | ----------- | ---------- | ----------------------------------------------------------------------- |
| **Voice Sensitivity** | 0.10 – 0.90 | **0.50** | How confident the detector must be that it hears a voice. |
| **Remove Silences Over** | 0 – 2 s | **0.20 s** | Silences shorter than this are left alone. |
| **Keep Segments Over** | 0 – 2 s | **0.20 s** | Speech chunks shorter than this are treated as noise and removed. |
| **Padding** | -1 – 2 s | **0.10 s** | Margin added before and after every kept segment. |
| **Split L/R Padding** | toggle | off | Splits Padding into independent **Padding Left** and **Padding Right**. |
**Voice Sensitivity replaces the old "Silence Cutoff" (dB) setting.** It is no longer a volume threshold: the tool detects *voice*, so background noise, room tone or music no longer count as "not silent". Higher value = stricter = cuts more.
### Voice Sensitivity
* **0.10 – 0.30** — very permissive. Keeps whispers, soft-spoken delivery, ASMR, quiet interviews. Use when the tool is eating the beginning of your words.
* **0.40 – 0.60** — balanced. Standard talking-head, podcast, tutorial. **Start here.**
* **0.70 – 0.90** — strict. Cuts aggressively; useful in noisy rooms, with air conditioning, street noise or a loud music bed where the detector is too generous.
If the cut sounds *clipped* — the first syllable is missing — lower the sensitivity before touching padding. If it sounds *sloppy*, with breaths and hesitations surviving, raise it.
### Remove Silences Over
The minimum length a silence must reach before it's worth cutting.
* **0.10 – 0.20 s** — very tight, machine-gun pacing. Great for social/vertical edits.
* **0.30 – 0.60 s** — natural rhythm. Removes the dead air but keeps the breathing room of speech.
* **1 s and above** — only removes the long pauses. Good for interviews where the silences carry meaning.
### Keep Segments Over
Anything shorter than this is not considered real speech: a lip smack, a click, a door, a cough between two sentences. Raise it if isolated noises are kept as tiny orphan clips; keep it low if you have short interjections ("yes", "no", "hm") that must survive.
### Padding
Padding gives each kept segment a bit of air, so cuts don't feel surgical.
* **Positive values (0.05 – 0.30 s)** — the usual case. Extends each segment on both sides.
* **0** — hard, immediate cuts. Maximum tightness, harsher listening.
* **Negative values (down to -1 s)** — shrinks the kept segments, cutting *into* the speech. Only for very aggressive stylistic edits — it will clip words.
Turn on **Split L/R Padding** to get the most natural result: a **small left padding** (0.05 s, so the attack of the word isn't chopped) and a **larger right padding** (0.15–0.25 s, so the end of the sentence can breathe).
### Presets
The preset bar at the top of Step 1 saves your whole slider configuration under a name and reloads it in one click. Build one per format — *Podcast*, *Reels*, *Interview* — instead of re-tuning every session.
## Step 2 — Preview
The preview analyses a **15-second sample** taken at the playhead and is **free** — it doesn't consume credits, so you can run it as often as you like.
Blue = kept. **Red overlay = removed.** The picture reflects your current sliders in real time.
Hit the green play button, or click anywhere on the waveform to jump there and audition the passage.
Moving a slider after a preview **does not** require a new analysis — the cuts are recomputed locally and instantly. Only click **Preview** again if you move the playhead to a different part of the sequence.
Preview the hardest part of your footage, not the easiest: the passage where you hesitate, where the room is noisy, or where you speak softly. Settings that survive there will work everywhere.
## Step 3 — Apply to timeline
Analyses the **whole sequence** and applies the cuts. A **backup of your sequence is created automatically** beforehand, so you can always go back.
Jump Cut disables the silent clips instead of deleting them, so you can review the result. Click **Delete Disabled Clips** to remove them and close the gaps.
Tick the checkbox on that same button to **auto-delete** at the end of every run.
**On DaVinci Resolve**, the *Delete Disabled Clips* control is hidden — and that's expected. Resolve rebuilds a new timeline containing only the kept segments, so there is nothing left to delete.
## From the Copilot
You can also just ask in the chat:
> *"Remove the silences from my sequence."*
The Copilot runs the same engine with sensible defaults. Use the panel when you want to see the waveform and dial the pacing in yourself.
## Common Pitfalls
* **Playhead over a silent or music-only area** → the preview sample contains no speech and looks entirely red. Move it over real dialogue.
* **Words getting clipped** → lower **Voice Sensitivity**, then raise **Padding Left**. In that order.
* **Breaths and hesitations surviving** → raise **Voice Sensitivity** and lower **Remove Silences Over**.
* **Tiny orphan clips left over** → raise **Keep Segments Over**.
* **Loud music bed under the voice** → voice detection struggles. Mute or lower the music track before running, or push the sensitivity up.
* **Negative padding** eats into speech by design — it is not a "tighter" setting, it's a destructive one.
**Recommended starting point** for a talking-head edit: Voice Sensitivity **0.5**, Remove Silences Over **0.3 s**, Keep Segments Over **0.2 s**, Split L/R Padding **on** with **0.05 s** left and **0.20 s** right.
# Multicam Podcast Editing
Source: https://docs.premierecopilot.com/features/multicam-editing
Automatically cut a synchronized multicamera podcast by following the active speaker.
Podcast automatically edits a synchronized multicamera conversation by detecting who is speaking and selecting an appropriate camera for each moment.
The preparation matters more than any setting. Build a clean synchronized sequence before running the tool.
## Prepare the timeline
* Create exactly **one audio track with voice clips per speaker**.
* Each speaker track must contain only that person’s voice, not the full mix.
* Synchronize every audio and video track before starting.
* For best results, nest the clips on each audio and video track so each track contains one continuous clip.
* Avoid placing nested sequences inside those clips.
![Timeline setup for podcast editing]()
## Quick Start
Match the speaker count to the voice tracks and the camera count to the video tracks.
Name every speaker and select the audio track that contains their isolated voice.
For every video track, select the speakers visible in that shot and how frequently the camera should appear.
Decide whether unused material should be disabled or cut, and whether the operation should also affect audio.
Click **Start Editing Podcast** and leave the timeline untouched until processing finishes.
## Camera assignments
A camera can be assigned to one speaker, several speakers, or all speakers. Use this to describe close-ups, two-shots, and wide shots. The frequency setting controls how often that camera may be selected relative to the others.
Assign wide shots to every visible speaker and give them a lower frequency than close-ups. They will then act as occasional breathing shots instead of replacing the main coverage.
## Cutting methods
| Method | Result |
| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
| **Disable Clips** | Keeps the original material but disables the portions that are not selected. This is the safest option for later adjustments. |
| **Disable Audio & Clips** | Applies the speaker edit to video and audio. The optional **Link V/A** setting keeps linked material together. |
| **Standard** | Performs a conventional cut-based edit. |
## Advanced settings
| Setting | What it changes |
| --------------------- | ---------------------------------------------------------------------------------- |
| **Delay Cuts** | Waits briefly before changing camera so cuts feel less abrupt. |
| **Ignore Small** | Ignores very short speaking turns that would create distracting micro-cuts. |
| **Smoothing** | Stabilizes speaker detection during pauses, room noise, and uncertain transitions. |
| **Min Cut / Max Cut** | Keeps shot lengths within a preferred range. |
| **Frequency Weights** | Controls the relative use of cameras marked High, Medium, Low, or Very Low. |
Saved presets remember the complete setup, which is useful for recurring shows with the same tracks and camera layout.
## Common pitfalls
* **A full mix on every audio track** prevents reliable speaker detection.
* **The wrong speaker assigned to a track** produces camera changes for the wrong person.
* **A camera with no speaker assigned** cannot be selected meaningfully.
* **Very short shot limits** create a nervous edit; increase Ignore Small or Min Cut.
* **Editing during processing** can invalidate synchronization and cut positions.
Start with Disable Clips, moderate smoothing, and conservative camera frequencies. Review the generated edit once, then adjust only the few cuts that do not match your editorial intention.
# Smart Captions
Source: https://docs.premierecopilot.com/features/smart-captions
Styled, animated captions burned onto your timeline — karaoke highlighting, boxes, shadows, emojis.
Smart Captions turns your sequence into styled captions on the timeline: word-by-word karaoke highlighting, boxes, strokes, shadows, pop animations and auto-placed emojis — the social-video caption look, rendered and placed for you.
It works in two stages: **transcribe and edit the text**, then **design the look**. The first stage is the exact same editor as [Subtitles Pro](/features/subtitles-pro) — this page covers the design stage.
Works in **Premiere Pro** and **DaVinci Resolve**.
## Quick Start
Open **Smart Captions**, set the language and caption limits, and click **Transcribe**. See [Subtitles Pro](/features/subtitles-pro) for the transcription settings — they're identical.
Correct any wrong words and caption breaks now. Text is not editable after the captions are rendered.
Click **Auto Emojis** to have one picked per caption. The **Animated** switch makes them animated emojis.
Click **Design Captions** to open the style panel.
Adjust the design — the preview updates on a real frame from your timeline.
Pick an **Export Location**, then click **Apply to Project**.
Smart Captions handles sequences up to **30 minutes**. Rendering animated captions is far heavier than a plain transcription, hence the tighter limit than Subtitles Pro.
Captions arrive as **rendered clips**, not editable text layers. You can move, trim or delete them, but you cannot retype a word. Get the text right before you leave the transcription stage.
## The design panel
### Preview
The preview shows your captions over a **real frame from your timeline**. Two buttons sit in its corner:
* **Refresh Styles** — re-renders the caption with your current settings.
* **Refresh Timeline Frame** — grabs a new frame at the playhead.
**Drag the caption in the preview** to set where it sits in frame. Drag the emoji to place it independently.
Refresh the timeline frame onto your *busiest* shot, not a clean one. Captions that stay readable over the worst background are readable everywhere.
### Typography
| Control | Range | Notes |
| -------------------------------------------- | -------------------- | --------------------------------------------------------------------------- |
| **Font** | your installed fonts | The actual font file is used for the render — what you see is what you get. |
| **Size** | 20–300 | Relative to your sequence resolution. |
| **Nb Lines** | 1–3 | How many lines a caption wraps onto. |
| **Letter Spacing** | -10–50 | Negative tightens. |
| **?** button | toggle | Strips punctuation from the captions. |
| **TT** button | toggle | ALL CAPS. |
| **Text Color / Stroke Color / Stroke Width** | 0–20 | A stroke is what keeps text readable over any background. |
For social captions: a heavy sans, ALL CAPS, punctuation off, and a stroke of 4–8. Those four choices do most of the work.
### Subtitles Box
A background panel behind the whole caption: background and stroke colours, **Opacity**, **Radius**, **Pad Top / Pad Bot / Padding H**, **Stroke Width**.
Use it when your footage is bright or busy and a text stroke alone isn't enough.
### Shadow
**Color**, **Opacity**, **Softness** (0–20), **Distance** (0–50), **Angle** (0–360).
A soft, near-black shadow at low distance separates text from the image far more subtly than a box. Big distances read as a 90s title effect.
### Active Word
This is the karaoke effect — the word currently being spoken is highlighted.
| Control | What it does |
| -------------------------- | ------------------------------------------------------------ |
| **Active Color** | Colour of the word being spoken. |
| **Left Side / Right Side** | Colour of the words already said and the ones still to come. |
| **Active Scale** | 100–200% — how much the active word grows. |
Dimming the **Left Side** and **Right Side** colours while keeping the active word bright creates the follow-along effect that keeps viewers reading. Keep Active Scale near 110–130% — above that the line reflows visibly on every word.
### Active Box
A box drawn behind the active word instead of the whole caption: colours, opacity, radius, vertical and horizontal padding, stroke.
Active Box and Subtitles Box can be combined, but a box behind a box on a stroked font is usually one effect too many. Pick the one that carries the look.
### Animations
* **Zoom In** — the caption pops in.
* **Motion Blur** — adds blur to the movement.
### Emojis
Enable the section, then set **Emoji Scale** (50–200%) and **Pos X / Pos Y**. The emojis themselves come from the **Auto Emojis** button back in the transcription stage — turn the section on here without having generated them and nothing appears.
Place emojis just above the caption rather than beside it: side placement shifts with every caption width, top placement stays visually stable.
## Presets
The preset bar at the bottom saves your whole design and reloads it in one click. Build one per channel or per format — it's the difference between a five-minute setup and a thirty-second one on every video.
## Apply to Project
Set an **Export Location**, then click **Apply to Project**. The captions are rendered, downloaded to that folder, and placed on your timeline.
The render can take a while and the host app may look frozen near the end while the clips are placed. Let it finish.
## Common Pitfalls
* **Sequence longer than 30 minutes** → refused. Use [Subtitles Pro](/features/subtitles-pro) with an SRT instead, or split the sequence.
* **Text typo spotted after applying** → undo, go **Back** to the transcription, fix it, and re-apply. It cannot be fixed on the timeline.
* **Emojis section on but no emojis visible** → run **Auto Emojis** in the transcription stage first.
* **Captions unreadable on light footage** → add a stroke first, a shadow second, a box last.
* **Caption size looks wrong** → it scales with sequence resolution. Re-check on a vertical sequence after designing on a horizontal one.
* **Font missing from the list** → only fonts installed on your machine appear. Install it, then reopen the panel.
* **Flickering captions** → raise **Max Gap** in the transcription stage; tiny gaps between words fragment the captions.
**Recommended workflow:** transcribe → fix the text completely → Auto Emojis → design on your busiest frame → save a preset → Apply to Project.
# Smart Chapters
Source: https://docs.premierecopilot.com/features/smart-chapters
Turn a finished video into clear YouTube chapters with titles, timestamps, and optional timeline markers.
Smart Chapters reads the spoken content of your active sequence and creates a structured list of YouTube chapters with clear titles and timestamps.
You can copy the list directly into a video description and optionally add the chapters as markers on the timeline.
## Quick Start
Make the video you want to chapter active and check that its dialogue is clear.
Choose the minimum and maximum number of chapters you want.
Mention important topics or ask for a particular structure.
Click **Generate Chapters** and keep the editing application open while the sequence is processed.
Click **Copy text** for your video description, or **Add Markers** to place the chapter titles on the timeline.
## Settings
| Setting | Range | What it does |
| ---------------- | ------------- | ----------------------------------------------------------------------- |
| **Min Chapters** | 1–30 | Minimum number of sections the tool should identify. |
| **Max Chapters** | up to 50 | Maximum number of sections it may return. |
| **Brief** | optional text | Gives context, names important topics, or requests a specific grouping. |
The first chapter begins at `00:00`, which is required by YouTube chapter formatting.
Do not force too many chapters. A chapter should represent a real topic change, not every short pause or example.
## Writing a useful brief
* *“Separate the introduction, tutorial, pricing discussion, and conclusion.”*
* *“Keep every product demo as its own chapter.”*
* *“Use short, factual titles and keep the sponsor section separate.”*
The brief guides the organization. It does not replace the actual spoken content and cannot create chapters for topics that are not present.
## Review and export
Read the generated titles and check their timecodes before publishing. **Copy text** copies the complete chapter list in a format suitable for a description. **Add Markers** places each title at its timestamp on the active timeline.
Adding markers does not cut or rearrange the sequence. It only adds navigation points.
## Common pitfalls
* **Unclear or missing dialogue** produces weak chapter boundaries.
* **A very high minimum** can split one topic into several artificial chapters.
* **A very low maximum** can merge unrelated topics.
* **Changing the sequence after generation** makes the timestamps outdated. Generate again after major edits.
* **Editing during processing** can cause the analyzed audio to differ from the current timeline.
For a 10 to 30 minute video, start with 5 minimum and 10 maximum chapters, then regenerate with a more specific brief only if the structure is too broad.
# Smart Diarization
Source: https://docs.premierecopilot.com/features/smart-diarization
Detect the speakers in a mixed recording and rebuild the edit with one audio track per speaker.
Smart Diarization detects who speaks when in a mixed recording, lets you review the detected speakers, then creates a new sequence with one audio track per speaker.
It is useful when you received a single mixed audio file but need separate speaker tracks for editing, mixing, captions, or multicam preparation.
## Quick Start
Make the sequence containing the mixed conversation active.
Select a permanent folder next to your project, or leave the field empty to use the Premiere Copilot folder in Documents.
Click **Detect Speakers** and wait for the audio export and speaker detection to finish.
Check the number of detected segments and speaking time. Click a speaker to jump to their first line.
Click **Split Speakers** to create the new speaker sequence.
The exported audio file becomes the media used by the new sequence. Do not delete or move it after the split unless you relink it in your editing software.
## What the result contains
The review displays each detected speaker with:
* A speaker name.
* The destination audio track.
* The number of speaking segments.
* The total speaking time.
* A shortcut to the first detected line.
When applied, the tool imports the exported audio and builds a new sequence in which each speaker is heard only on their assigned track. Your original sequence remains available.
Speaker detection separates voices by identity, not by microphone name. If two people sound very similar or speak over each other frequently, review the result carefully.
## Choosing the export folder
Use a folder that will stay with the project. The default Premiere Copilot folder is suitable for local work, while a dedicated media folder next to the project is safer for archiving or handing the project to another editor.
Saved presets remember your preferred export folder.
## Best source material
Smart Diarization works best when:
* Each person has a distinct voice.
* Dialogue is louder than music and background noise.
* Speakers do not constantly talk over one another.
* The sequence contains continuous, online audio.
## Common pitfalls
* **Music under the conversation** can be interpreted as part of the mix and reduce separation quality.
* **Heavy overlap between speakers** makes the boundary between voices uncertain.
* **Deleting the exported audio** takes the new sequence offline.
* **Applying before review** can create an unnecessary sequence when the detected speaker count is wrong.
* **Editing during processing** can invalidate the timing used to rebuild the tracks.
For the cleanest result, duplicate the source sequence, mute music and sound effects, run Smart Diarization on dialogue only, then use the separated sequence in your final edit.
# Smart Virals
Source: https://docs.premierecopilot.com/features/smart-virals
Find the strongest moments in a long video, or assemble them into reels, and turn them into vertical clips — captions included.
Smart Virals analyzes a long sequence, identifies the moments most likely to work as short-form content, and creates separate vertical clips from the ones you approve. It can hand you ready-made passages, or build complete reels by stitching several moments together — and caption every clip in the same run.
It is designed for podcasts, interviews, talking-head videos, webinars, and any long edit that contains reusable highlights.
Works in **Premiere Pro** and **DaVinci Resolve**.
## Quick Start
Open the long-form sequence, then pick **Whole timeline** or **In / Out** to analyze only the part between your In and Out points.
**Ready-made clips** finds self-contained passages. **Assembled reels** builds each reel from several moments of the video.
Choose how many clips or reels you want, the target durations and the signals, and add an optional brief.
Click **Start Analysis**. Open each result to read its full transcript and see exactly where it is cut, then deselect anything you do not want.
Click **Create Virals** to create one vertical sequence per selected result — or **Design Captions** to caption them in the same run.
The analyzed range must be under **2 hours**.
## Range
Smart Virals starts with a single choice, like Smart Captions:
* **Whole timeline** — analyzes the sequence from start to end.
* **In / Out** — analyzes only the range between your In and Out points. Set valid In and Out points first; the selected range length is displayed under the choice.
The range is read again when you click **Start Analysis**, so you can adjust your In and Out points after choosing.
## Formats
### Ready-made clips
Each result is one continuous passage of your video that works on its own — cut as is from the timeline.
### Assembled reels
Each result is a **reel built from 3 to 5 moments** taken anywhere in the video and played in the order that retains viewers on short-form platforms:
| Part | Role |
| ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Hook** | Always first. One or two sentences that stop the scroll and open a question — a bold claim, a surprising number, a confession, or the punchline used as a teaser. It can come from later in the video. |
| **Development** | One to three parts. The minimum context, then the substance: the story, the explanation, the steps. |
| **Payoff** | Usually one part. The answer, the result, the lesson — what the hook promised. |
| **Call to action** | Always last. An explicit ask when the speaker makes one, otherwise the strongest closing line: a question to the audience, a challenge, a quotable sentence. |
The total length of each reel targets your **Duration** ranges. Every reel tells a different story; the same strong hook or closing line can be reused across several reels when it genuinely fits.
Assembled reels are built from what is said, so the **Transcript** signal stays on in this format.
## Settings
| Setting | What it does |
| ----------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- |
| **Format** | **Ready-made clips** or **Assembled reels** (see above). |
| **Model** | How deeply the AI analyzes the video. Higher levels reason better on long videos and subtler moments. |
| **Clips Expected / Reels expected** | Number of distinct results to return, from 1 to 20. |
| **Duration** | Target length of each clip — or the total length of each reel, all parts combined. Enable several ranges to give the tool more flexibility. |
| **Emotion** | Favors moments with stronger vocal emotion. |
| **Cut Frequency** | Favors visually active passages with more edits. |
| **Transcript** | Favors strong ideas, stories, explanations, and punchlines in the spoken content. |
| **Brief** | Guides the selection toward a topic, tone, or editorial goal. The paste button inserts your clipboard. |
| **Disable AutoReframe** | Keeps the original framing instead of automatically reframing the extracts vertically. |
**Presets** save the whole configuration, format and brief included. Once the analysis has returned results, the settings fold away to make room for the review; reopen them with the arrow next to the preset menu.
Ask for more results than you intend to publish. Reviewing six candidates to keep three is usually more useful than asking for exactly three.
## Reviewing results
Each result shows a score, its final duration, badges for the strongest detected signals and the start of its transcript. Assembled reels also show a working title and their number of parts.
* **Click a row** to move the playhead to that moment (the hook, for a reel).
* **Use the checkbox** to include or exclude it.
* **Hover the line between two results** — it turns green and shows a **+**. Click it to expand the result above:
* for a ready-made clip, the full transcript, with the words just before and after it greyed out and a **green bar at each cut**;
* for an assembled reel, every part in playback order, highlighted by role — **Hook** green, **Development** blue, **Payoff** orange, **Call to action** purple — with its timecode and a **green bar at each cut**. Click a part to move the playhead to it.
**Add markers** places the selected results on the current sequence without creating anything. For an assembled reel, each part gets its own marker, colored by role.
### Create from In / Out
Use **Create from In/Out** when you already know the exact passage you want. Set the In and Out points in the sequence, then click the button to create that extract without running the analysis.
## Creating the clips
**Create Virals** creates one **vertical sequence (1080 × 1920)** per selected result, with AutoReframe (Premiere Pro) or Smart Reframe (DaVinci Resolve) applied unless you disabled it.
For an assembled reel, the parts are placed back to back in their playback order. In Premiere Pro, each part is kept as a nested sequence stored in the **Smart Virals parts** bin, so you can still open and trim it.
## Captioning the virals
Click **Design Captions** after the review to caption every selected result in the same run. The steps open one after the other in the same panel, and the view scrolls down to each new one:
**Analysis transcript** reuses the transcription made during the analysis — free, no new transcription. It requires the **Transcript** signal. **New transcription** transcribes each viral again with the engine of your choice, for sharper timing; it is billed per viral.
The same settings as [Subtitles Pro](/features/subtitles-pro): context and language for a new transcription, then caption length, gaps and punctuation.
**PremiereGPT** renders fully styled captions (shadows, box outlines, effects). **Premiere Pro** creates editable text layers. In DaVinci Resolve this step is skipped: captions are always rendered.
The [Smart Captions](/features/smart-captions) design panel, with a preview using words from your selected results.
The button shows the total price for all selected virals. It creates the vertical sequences, then transcribes (if needed) and captions each of them.
A progress window follows each step and shows the passage being processed. The original sequence is reopened at the end.
## Writing a useful brief
Good briefs state what deserves attention and what should be ignored:
* *“Focus on practical advice and surprising numbers. Skip the intro and sponsor section.”*
* *“Prioritize funny disagreements and complete stories with a clear payoff.”*
* *“Only select moments about the product launch.”*
For assembled reels, you can also describe the story you want: *“Build reels around the three biggest mistakes, each ending on the fix.”*
Avoid exact timecodes in the brief. Use the **In / Out** range when you already know the part of the video to analyze.
## Common pitfalls
* **Weak or mixed dialogue** reduces the quality of the selected moments.
* **Too few duration ranges** can make good passages or good assemblies impossible to fit.
* **AutoReframe disabled** keeps the source framing, which may not suit a vertical sequence.
* **Creating every result** defeats the review step. Expand each result and check its cuts before creating it.
* **Editing the timeline during processing** can shift the selected timecodes.
Recommended workflow: request 5 to 8 results, enable two duration ranges, analyze with Transcript plus one supporting signal, add a short brief, expand each result to check its cuts, then keep only the clips with a complete idea and a clean ending.
# Spelling
Source: https://docs.premierecopilot.com/features/spelling
Find spelling and grammar mistakes in captions, titles, and motion graphics without overwriting your edit.
Spelling reads the text in your active sequence, detects its language, and lists spelling or grammar corrections with their timecodes.
It checks captions, native titles, and editable text inside motion graphics. Corrections remain suggestions: the tool never overwrites your project text.
## Quick Start
Make the sequence active. The project is saved before its text is read.
List names, brands, places, products, or writing rules that must be respected.
Click **Check spelling**. The language is detected automatically.
Compare the original and suggested text, then click **Go to & copy** to move to the item and copy the correction.
Paste or type the correction in your editing software, then mark the suggestion as validated.
## Use the context field
The context field prevents intentional words from being treated as mistakes and tells the checker which writing style to follow.
Useful context includes:
* *“Premiere Copilot, AutoZoom, and Kwerty are product names.”*
* *“Keep English technical terms in this French video.”*
* *“Use formal language and inclusive writing.”*
* *“Do not change capitalization in brand names.”*
Add proper nouns before the first check. This removes more false positives than reviewing them one by one afterward.
## Review controls
Each correction contains its timecode, text type, original text, suggested replacement, and an explanation when useful.
| Action | What it does |
| ----------------- | --------------------------------------------------------------- |
| **Click the row** | Moves the playhead to the corresponding text. |
| **Go to & copy** | Moves to the item and copies the corrected text. |
| **Validate** | Marks the suggestion as reviewed without changing the timeline. |
| **Copy** | Copies all corrections to the clipboard. |
| **Reset** | Clears the current result list. |
Because corrections are applied manually, you can keep the exact typography, animation, and formatting of every title.
## Common pitfalls
* **Text stored as a flattened image or video** cannot be read.
* **Protected names missing from Context** may be suggested as corrections.
* **Validate does not edit the text**; it only tracks your review progress.
* **Changing the sequence after the check** can make displayed timecodes outdated.
Review names and numbers first, then punctuation, then stylistic grammar suggestions. This order catches the most visible mistakes quickly.
# Subtitles Pro
Source: https://docs.premierecopilot.com/features/subtitles-pro
Transcribe your sequence, edit the transcript word by word, translate it, and export a clean SRT.
Subtitles Pro transcribes your sequence and gives you a real editor on top of it: fix a word, move a line break, split or merge captions, run a find & replace, translate into another language, then export an SRT.
It is the **text** half of PremiereGPT's caption tooling. If you want styled, burned-in captions on your timeline, use [Smart Captions](/features/smart-captions) — it shares this exact editor and adds a design step.
Works in **Premiere Pro** and **DaVinci Resolve**.
## Quick Start
Open **Subtitles Pro** from the Tools Menu, with your sequence open.
Pick the spoken **Language** (or leave it on Auto), then set **Max Chars** and **Max Gap** to shape how captions are cut.
Click **Transcribe**. The chevron on its left lets you pick a different engine first.
Fix anything that's wrong directly in the transcript — words, breaks, punctuation, casing.
Click **Generate SRT**. The file lands in your export folder.
Subtitles Pro handles sequences up to **2 hours**. Longer ones are refused before any work starts.
## Settings
### General
| Setting | Range | What it does |
| ------------- | ----------- | -------------------------------------------------------------------------------------- |
| **Max Chars** | 5–100 | Maximum characters per caption. This is the main lever on caption length. |
| **Max Gap** | 0–2 s | Silences shorter than this don't break a caption — the line keeps running across them. |
| **Language** | Auto + list | The **spoken** language of your audio. |
Naming the language explicitly beats **Auto** whenever you know it — especially on accented speech, technical vocabulary, or audio that starts with music or silence.
**Max Chars** by format:
* **15–25** — one short line at a time, social / vertical style.
* **30–45** — the classic subtitle range. Comfortable to read, matches broadcast habits.
* **50+** — long lines for wide screens and dense dialogue.
**Max Gap** shapes rhythm: a low value cuts a new caption at every small pause (choppy but precise), a high value keeps sentences together across breaths (smoother, longer captions).
### Correction
| Setting | What it does |
| ------------ | ------------------------------------------------------------------ |
| **Model** | GPT-5.3 or GPT-4.1 — the model that proofreads the raw transcript. |
| **Spelling** | Turn the correction pass on or off. |
The correction pass fixes spelling, punctuation and obvious transcription slips. Turn it **off** only if you want the raw output untouched — for example when you'll be conforming to an existing script by hand.
### SRT Export
| Setting | Range | What it does |
| --------------- | -------- | ------------------------------------------------------------ |
| **Lines** | 1–3 | How many lines each subtitle is wrapped onto. |
| **Solo Punct.** | on / off | Keeps punctuation from being stranded alone on its own line. |
### AI Context
A free-text box (up to 800 characters) read by the transcription itself. This is where you protect the words a generic model will get wrong.
**What to put in it:**
* **Proper nouns:** *"The company is called Kwerty, the CEO is Anaïs Rouvier."*
* **Product and brand names:** *"Our products: FlowKit, FlowKit Pro, DeskSync."*
* **Jargon and acronyms:** *"We say ARR, MRR, ICP, and 'go-to-market' spelled with hyphens."*
* **Preferred spelling:** *"Write 'e-mail', not 'email'."*
* **Language mixing:** *"French speech with English tech terms — keep the English terms in English."*
**What not to put in it:** styling, caption length, translation requests or editing instructions — none of that is read here. Length is Max Chars; style lives in Smart Captions.
A list of ten proper nouns in this box removes more errors than any engine upgrade. It is the cheapest quality win in the tool.
## Transcription engines
The chevron to the left of **Transcribe** opens three mutually exclusive engines:
Standard engine — fast and reliable. The default, and the right choice almost every time.
Re-syncs every word to the audio with forced alignment. Sharper timing, slightly slower, extra credits.
The most accurate engine — and much more expensive. Only worth it when the standard engine genuinely isn't good enough.
Pick by symptom: **wrong words** → V2 (or better AI Context first). **Right words, drifting timing** → advanced word precision. Anything else → standard.
## Editing the transcript
The editor is the point of the tool. Everything below is instant and local — no re-transcription.
| Action | Effect |
| --------------------------- | ----------------------------------------------------------- |
| **Click a word** | Edit its text inline. |
| **Click between two words** | Insert or remove a caption break there. |
| **Drag a break** | Move it to another position. |
| **Find & Replace** | Fix a recurring name across the whole transcript in one go. |
| **Punctuation toggle** | Strip all punctuation (commas included) or restore it. |
| **Capitals toggle** | Switch between original casing and all-lowercase. |
| **Split at punctuation** | Automatically break captions at punctuation marks. |
Fix recurring errors with **Find & Replace** before touching anything by hand — a misheard brand name usually appears a dozen times.
## Translation
Pick a target language in the widget at the bottom right and click **Translate**. The translation is created as a **new version**: the arrows next to it let you move between versions, and the original is never lost.
Each version keeps its own timing, so you can generate an SRT per language from the same transcription without re-running it.
## Importing an existing SRT
**Import SRT** loads an existing subtitle file as the working transcription. Use it to fix, re-time, translate or re-style subtitles that came from elsewhere, without paying for a transcription.
## Common Pitfalls
* **Sequence longer than 2 hours** → refused up front. Split it, or work sequence by sequence.
* **Language left on Auto with a multilingual take** → mixed-up output. Set the dominant language and describe the mixing in AI Context.
* **Proper nouns wrong after a run** → they belong in AI Context; re-transcribing without it changes nothing.
* **Music or loud background under the voice** → transcription quality drops. Mute those tracks before running.
* **Editing after translating** → each version is independent. Fix the source first, then translate.
* **AI Context over 800 characters** is cut off. Keep it to the words that actually matter.
**Recommended workflow:** set the language → write ten lines of AI Context → standard engine → transcribe → Find & Replace the recurring errors → adjust Max Chars → Generate SRT.
# Vibe Kinetic
Source: https://docs.premierecopilot.com/features/vibe-kinetic
AI kinetic text: animated captions and hooks rendered from your own words, placed on your timeline.
Vibe Kinetic listens to your sequence, picks the sentences worth putting on screen, art-directs them (typography, colour, animation, word-level highlights) and renders each one as an **animated clip with a transparent background**, placed automatically on your timeline.
It is not a subtitle tool. It writes **short on-screen hooks** — the punchline, the number, the payoff — the way a motion designer would, not a word-for-word transcript.
Works in **Premiere Pro** and **DaVinci Resolve**.
## Quick Start
Open the **Tools Menu** and select **Vibe Kinetic**.
Click a card in **Style presets** — it fills the **Brief** box with a ready-made style description you can then edit.
Describe the look and the editorial intent in plain language. Leave it empty for the clean default look.
**Texts per minute** = how many captions appear. **Seconds on screen** = how long each one stays.
Click **Generate captions**. The run modal shows four steps: audio export, curation, render, placement.
You need a **saved project** and an **active sequence with audio**. The tool reads the whole sequence, not just the part around the playhead.
## What you get on the timeline
Each caption arrives as its own **video clip with alpha**, stacked above your footage and cut to the exact in/out point the AI chose.
These are rendered clips, **not** Essential Graphics / Text layers. You can move, trim, delete or re-order them freely, but you **cannot retype the text** inside Premiere or Resolve. To change wording or style, adjust the brief and run again.
Rendered files are written to the **download folder** before import, so you keep a copy of every clip.
## Main Settings
| Setting | Range | What it does |
| --------------------- | --------- | -------------------------------------------------------------------------------- |
| **Brief** | free text | Describes the look *and* the editorial intent. The single most powerful control. |
| **Style presets** | 6 cards | Click to load a proven brief into the box. Fully editable afterwards. |
| **Texts per minute** | 2–15 | How dense the captions are. Default **8**. |
| **Seconds on screen** | 2–10 | Target display time per caption. Default **2**. |
| **Download folder** | folder | Where the rendered clips are stored. Defaults to your project folder. |
### Texts per minute
This is a **target density**, not a quota. The AI reasons in *ideas*, so it will only place a caption where there is something worth highlighting — a quiet or repetitive passage will get fewer.
Sparse, editorial. Long-form, interviews, documentary, corporate.
Balanced. YouTube talking-head, tutorials, podcasts clips. **Start here.**
Dense, high-energy. Reels, TikTok, Shorts, fast-cut promos.
Above 15 a caption would live less than four seconds on screen and nobody can read it — that's why the slider stops there.
### Seconds on screen
This is the **target** duration. A caption is automatically shortened when the next one arrives sooner, and captions that would end up too short to be readable are dropped rather than flashed.
* **2–3 s** — punchy, rhythmic, matches fast dense edits. Best default.
* **4–6 s** — the viewer has time to read a longer line. Good for stats, quotes, definitions.
* **7–10 s** — near-permanent lower third. Only useful at very low density, otherwise captions collide and get trimmed anyway.
Density and duration interact. High density + long duration = the duration wins on paper but gets clipped in practice. If you want long-lived captions, lower the density.
## Advanced Settings
Advanced is **off by default**, and that is a real mode — not just hidden fields.
The AI art-directs everything: it derives the palette and the mood from what is actually being said, varies placement per caption, and uses a font auto-detected on your machine.
Your palette, your placement and your font pool are respected. The AI still composes hierarchy, highlights and animation — but inside your constraints.
### Color palette
Four slots, plus five ready-made palettes.
| Slot | Typical role |
| ------------- | -------------------------------------------------------- |
| **Primary** | The body of the text — the colour most words will be. |
| **Secondary** | The accent: highlighted keywords, the payoff word. |
| **Third** | Secondary accent / a second line in a pairing. |
| **Fourth** | Support tone — muted lead-ins, decorations, panel tints. |
Fill **Primary + Secondary** and leave the rest empty if you only care about "white text, one brand-coloured keyword". Filling all four does not make the result busier — it just gives the art director more room.
Legibility is protected automatically: a colour that would vanish on its own background gets corrected. If your exact brand hex comes back slightly adjusted, that is why — pair it with a panel/box in the brief to keep it untouched.
### Placement
| Value | Behaviour | Use it when |
| ---------- | ---------------------------------------------- | ------------------------------------------------------------- |
| **Auto** | The AI varies the position caption by caption. | You want the composition to breathe and follow the frame. |
| **Top** | Every caption locked to the upper zone. | Subject's face or a lower-third graphic occupies the bottom. |
| **Center** | Every caption locked to the middle. | Full-screen statement style, B-roll montage, no talking head. |
| **Bottom** | Every caption locked to the lower zone. | Classic. Safest for readability. |
For vertical social exports, **Center** or **Top** is usually safer: platform UI (captions, username, buttons) covers the bottom of the frame.
### Fonts
The dropdown lists the fonts **installed on your machine**, and the exact font file is sent to the renderer so what you see is what you get. You can add **up to 3**.
* **1 font** — the safest, most coherent result.
* **2 fonts** — enables *pairing*: a small lead-in line in one face and a big payoff line in another. This is what makes a caption look designed rather than typed.
* **3 fonts** — extra material for the art director to choose from; useful when you're not sure which one fits your footage.
Typography stays **consistent across the whole video**: whatever the AI settles on for the first captions is applied to all of them, so the look never drifts halfway through. Multiple fonts create contrast *inside* a caption (line 1 vs line 2), not a different font every five seconds.
Pick a **heavy display or condensed** face for the payoff line and a **regular sans** for the lead-in. Pairing two similar sans faces produces contrast so weak it reads as a mistake.
### Download folder
Defaults to your **project folder** (marked `project`). Change it if your project lives on a slow network drive — rendering writes one file per caption, and a fast local disk keeps import snappy. **Reset** puts it back to the project folder.
## Writing a Good Brief
The brief is read as **art direction**, so describe what you want to *see*, not what you want the tool to *do*.
### What works
* **The container:** *"Put every caption on a solid white rounded card with generous padding and a soft shadow."*
* **The typography:** *"Bold white uppercase condensed text, tight tracking, sentence case for the lead-in."*
* **The composition:** *"Exactly two lines: a small lowercase lead-in, then a payoff about twice the size, lines almost touching."*
* **The motion:** *"Words rise one by one with a gentle ease-out, no scale change, no rotation."*
* **The restraint:** *"No outline, no glow, no tilt, nothing else on screen."*
* **The editorial intent:** *"Only highlight actionable advice and numbers. Skip pleasantries and transitions."*
* **The tone of the words:** *"Rewrite what I say into short punchy hooks, never full sentences."*
### What doesn't work
* **A manual list of timecodes or exact sentences** — the AI chooses the moments itself from what is said. If you already know the exact texts and timings, use the **Copilot** instead (see below).
* **Asking for more or fewer captions** — that's the *Texts per minute* slider.
* **Asking for a longer display time** — that's the *Seconds on screen* slider.
* **Asking for a font you didn't select** — only fonts installed and picked in Advanced are available.
* **Asking for images, logos, icons or video inside a caption** — the engine renders type, panels and effects, nothing else.
* **Vague vibes alone** (*"make it cool"*) — you'll get the default look. Name a colour, a weight, a shape, a motion.
### Recommended pattern
> *"\[Container]. \[Typography and case]. \[Composition / number of lines]. \[Motion and rhythm]. \[What to avoid]. \[What to highlight editorially]."*
**Example:**
> *"No box. Bold white uppercase condensed text in the lower third with a very discreet halo. One line only, never stacked. Words rise gently one by one, no scale, no rotation. Highlight only numbers and product names in a saturated accent. Nothing else on screen."*
Start from a **style preset**, run once, then edit two or three words of the brief and run again. Iterating on a working brief beats writing a perfect one from scratch.
## Style Presets
Clicking a preset only **fills the brief box** — nothing is locked. Edit it, merge two of them, or delete half a sentence.
| Preset | Look |
| ------------------ | ----------------------------------------------------------------------------------------------------- |
| **Institutional** | White rounded card, dark text, one line, soft shadow. Corporate, clean, very legible. |
| **Retro Button** | Sky-blue card, hard offset shadow, heavy black uppercase. Pops in as one block. |
| **Cinematic** | No box, white condensed uppercase in the lower third, discreet halo, slow restrained motion. |
| **Apple Message** | Blue iMessage-style bubble, white conversational text, springy pop-in. |
| **Grid + Pairing** | Paper card hugging the text, two lines, two fonts, a headline plus a handwritten accent. |
| **White Pairing** | No box, pure white with a soft bloom, small lead-in over a large uppercase payoff, word-by-word rise. |
## Using Vibe Kinetic from the Copilot
You can also ask the **Copilot** in chat to place animated text — it uses the same engine, but skips transcription and curation because *you* supply the words.
> *"Add kinetic text: 'ONLY 3 STEPS' at 4s, 'STEP ONE' at 9s, 'STEP TWO' at 15s — Apple style, white on two lines, 3 seconds each."*
What you can specify in the request:
| You provide | Notes |
| ------------------------------- | ---------------------------------------------------------------------------------------- |
| **The texts and their timings** | Required. Up to 200 items. |
| **A style brief** | Same language as the panel brief. |
| **Colours** | Given as a small palette. |
| **Placement** | `auto`, `top`, `center` or `bottom`. |
| **A font** | Free-form name — it is matched to a font available on your machine or to a built-in one. |
| **A target duration** | 2–10 s, applied to any text you left open-ended. |
Ask for a font by name and you'll get the closest real match, never a missing-font error. If nothing close is installed, a sane built-in face is used instead.
## Common Pitfalls
* **No sequence audio** → nothing to analyse, no captions. The panel path needs a spoken track.
* **Project not saved** → the download folder falls back to your temp directory; rendered clips still import, but they're stored outside your project.
* **Too dense + too long** → captions overlap and get trimmed or dropped. Lower the density before raising the duration.
* **All four palette slots set to near-identical colours** → highlights become invisible. Keep one clearly contrasting accent.
* **Advanced ON with no font selected** → the Generate button stays disabled. Pick at least one font.
* **Very long sequences** take a while: one clip is rendered per caption. A one-hour interview at 8/min is roughly 500 clips.
**Recommended starting point** for a talking-head social edit: pick **White Pairing** or **Cinematic**, density **8**, duration **2 s**, Advanced **ON** with one condensed display font plus one regular sans, placement **Center** for vertical / **Bottom** for horizontal.
# Vibe Motion
Source: https://docs.premierecopilot.com/features/vibe-motion
Create custom animated graphics, preview variations, and insert transparent motion-design clips into your timeline.
Vibe Motion creates custom motion graphics from a written brief or from key moments in your sequence. You preview the proposals, adjust exposed style controls, then export the chosen animation as a transparent clip on the timeline.
## Choose a mode
Reads the active sequence, proposes timed motion designs for important spoken moments, and lets you generate several selected designs in one run.
Creates three visual proposals for one animation described in your brief. Choose one, preview it, adjust it, and export it.
## Quick Start: Prompt mode
Set the format, frame rate, duration, background, and optional typeface.
Pick a style preset, then rewrite the brief so it describes your exact content and motion.
Click **Generate 3 options** and wait until the three cards finish.
Select one finished proposal and adjust the settings displayed below its preview.
Click **Export to timeline** to render, download, and import the animation.
## Quick Start: Audio based mode
The active sequence must contain clear spoken audio and be under 2 hours.
Choose **Designs per minute** and add one or more optional briefs. With several briefs, the tool chooses which style fits each passage.
Click **Analyze sequence** to receive timed design suggestions.
Click a suggestion to inspect its timecode and deselect anything you do not want.
Generate the selected designs. Each completed animation is placed at its proposed timecode.
## Main settings
| Setting | What it does |
| ----------------- | -------------------------------------------------------------------------------- |
| **Format** | Sets the aspect ratio of the rendered animation. Match the destination sequence. |
| **FPS** | Sets the export frame rate. Match the timeline to keep motion smooth. |
| **Duration** | Controls the exact animation length. |
| **Background** | Uses transparency for overlays or a solid background for full-frame designs. |
| **Typeface** | Lets you impose a font or leave the visual choice open. |
| **Images** | Adds visual references or assets to incorporate into the design. |
| **Color palette** | Restricts the design to your brand or project colors. |
| **Export folder** | Stores rendered clips before they are imported into the project. |
## Writing a strong brief
Describe the hierarchy, typography, composition, colors, and motion:
> *“Two-line title on transparent background. Small white lead-in above a large condensed green keyword. Enter from below with a soft overshoot, hold clearly, then fade out. No icons or extra decoration.”*
State the exact on-screen text when wording matters. Mention what must not appear. Avoid vague briefs such as *“make it dynamic.”*
Presets are starting points, not locked templates. Pick the closest one and replace its wording, colors, and movement instructions.
## Export behavior
The exported result is a rendered video clip, not an editable title layer. You can move, trim, duplicate, or delete it on the timeline, but changing the words or design requires a new export.
Use a transparent background when the design should sit above footage. Use a solid background for cards, title screens, or full-frame transitions.
## Common pitfalls
* **Frame rate does not match the sequence**: the animation may appear uneven.
* **Wrong aspect ratio**: the clip may need scaling or cropping after import.
* **Text is wrong after export**: correct it in the brief and generate again.
* **Too many audio-based designs**: lower Designs per minute and keep only the strongest suggestions.
* **Missing local asset or export folder**: keep referenced files available until rendering and import finish.
* **Editing during export**: leave the timeline untouched until placement is complete.
For overlays, start with transparency, the same FPS and aspect ratio as the sequence, a short duration, and a brief that names one focal animation only.
# Create an Account
Source: https://docs.premierecopilot.com/getting-started/create-account
Get started with Première Copilot by creating your account and accessing the dashboard.
## Creating an Account
To begin using Première Copilot, you must first create a user account.
Go to the [Première Copilot website](https://premierecopilot.com).
Click on the **"Download for free"** button located at the top right of the page.
Fill out the form with your first name, last name, and other required details.
Click **"Sign up"**.
**Verify your email:** Go to your inbox and validate your account by clicking the confirmation link.
**Note:** Upon signing up, you will receive a promo code to purchase the "Podcast" plugin at a discounted rate.
## Accessing the Dashboard
Once verified, return to the website and click **"Sign in"** to access your dashboard. From here, you can:
Download the latest version of the application.
Schedule a demo to learn more features.
Join our community on Discord.
Access your promo code for referrals.
![Dashboard Placeholder]()
# Setup Fal.ai API Key
Source: https://docs.premierecopilot.com/getting-started/fal-api-key
Generate and configure your Fal.ai API key to enable AI image and video generation features.
## Why Fal.ai?
PremiereGPT uses **Fal.ai** to provide state-of-the-art AI generation capabilities, including high-quality image and video generation (using models like FLUX, Kling, or Luma). To use these features, you need to connect your own Fal.ai account.
## Step 1: Create a Fal.ai Account
To get started, you need to register on the official Fal.ai platform.
Go to the [Fal.ai official website](https://fal.ai/).
Click on the **"Login"** or **"Get Started"** button in the top right corner.
Fal.ai uses OAuth for secure access. You can sign up using:
* **GitHub** (Recommended for developers)
* **Google**
Select your preferred provider to create your account instantly.
**Note:** New accounts often come with complimentary credits to test the models. Check your [Billing Dashboard](https://fal.ai/dashboard/billing) to see your balance.
## Step 2: Generate your API Key
Once your account is created, you can generate the secret key required by PremiereGPT.
Navigate to the [Fal.ai Dashboard](https://fal.ai/dashboard).
Click on the **"API Keys"** tab in the left sidebar or go directly to [fal.ai/dashboard/keys](https://fal.ai/dashboard/keys).
Click the **"Create Key"** button.
Give your key a name to remember where it is used (e.g., `PremiereGPT-Production`).
**Important:** Your API Key will only be displayed **once**.
* Click the copy icon next to the key.
* Save it in a secure location (like a password manager).
* If you lose it, you will have to delete it and create a new one.
**Security Warning:** Never share your API key or commit it to a public repository. Treat it like a password.
## Step 3: Configure PremiereGPT
Now that you have your key, you need to add it to PremiereGPT.
You can paste your API key in two places:
* **User Settings:** Open the **User Settings** panel in PremiereGPT and look for the **Fal.ai API Key** field.
* **API Modal:** Paste it directly into the configuration modal that appears when you first use an AI generation tool.
Find the dedicated field and paste your secret key. Note that while many keys start with `fal_`, this is not always the case.
Click **Save**. You can now start generating AI content directly in your timeline!
## Official Resources
For more detailed information, consult the official Fal.ai documentation:
* [Fal.ai Authentication Guide](https://fal.ai/docs/documentation/setting-up/authentication)
* [Managing API Keys](https://fal.ai/docs/platform-apis/v1/keys/create)
* [How to add Credits / Billing](https://fal.ai/dashboard/billing)
**Pro-Tip:** Make sure you copied the entire string from the dashboard. You can verify your key is working by attempting to generate a simple image or searching for a model in the library.
# Installation & Setup
Source: https://docs.premierecopilot.com/getting-started/installation
Download, install and initialize Première Copilot on your system.
## Downloading the App
Log in to your **Première Copilot Account**.
Click the **"Download App"** button.
Select the correct installer for your operating system:
* **Windows**
* **Mac Intel** (Older models)
* **Mac Silicon** (M1, M2, M3, M4 chips) — *Please ensure you select the correct architecture*.
## Installing the Software
**Unzip** the downloaded file.
**Run the installer**. This will install Première GPT in the correct directory.
**Restart Adobe Premiere Pro**. It is also recommended, though not mandatory, to restart your computer.
**Security Disclaimer:** You may receive a virus alert from Windows or Mac security. This is a false positive caused by the software being new and not yet fully whitelisted by manufacturers. The software is safe. Please authorize the application in your security settings to proceed.
## Initializing the Extension
Open Adobe Premiere Pro.
Go to **Window > Extensions > Première GPT Beta**.
**Log in** using the same credentials created on the website.
**First Launch:** If this is your first time starting the extension, allow 1–2 minutes for the backend engine to initialize. Subsequent launches will be much faster.
![Extension Menu Placeholder]()
# Introduction
Source: https://docs.premierecopilot.com/getting-started/introduction
Welcome to PremiereGPT documentation
# Welcome to PremiereGPT
This is the official documentation for PremiereGPT.
## Getting Started
Check out the [Create an Account](/getting-started/create-account) guide to get started.
# Affiliate Program
Source: https://docs.premierecopilot.com/support/affiliate
Earn 33% commission on sales generated through your referrals.
Earn **33% commission** on sales generated through your referrals.
## Eligibility
To become an affiliate, you must:
* Have an active account.
* Have purchased at least one product (Subscription or Podcast plugin).
## How it Works
Locate your **custom promo code** in your dashboard.
Share this code and the link with your contacts.
If a contact makes a purchase using your code (or on your recommendation), send an email to support containing the **email addresses of the contacts who created an account**.
Verification will be performed on our end to confirm the referral.
## Payouts
* **Commission Rate:** 33% of the amount paid.
* **Recurring:** Applicable monthly if the user subscribes.
* **Payment Methods:** Payouts are made via PayPal or Stripe refund.
# Support & Community
Source: https://docs.premierecopilot.com/support/community
Get help and join the Premiere Copilot community.
If you require assistance, we have several channels available to help you.
Accessible via the Dashboard or the "Join Discord" button.
Click "Book a demo" in your account to schedule a session.
Contact us directly at `admin@premieregpt.com` for specific inquiries.
# Copilot doesn't start
Source: https://docs.premierecopilot.com/support/copilot-doesnt-start
Listing of known bugs and best practices to follow if the extension doesn't launch.
If you are having trouble launching Premiere Copilot, here are the solutions to the most common problems.
## 1. Using a VPN
If you are using a **VPN**, it can sometimes block the local connection between the extension and its computation engine.
Disable your VPN and try restarting the extension.
## 2. First Launch (Waiting)
During the very first launch, the extension must initialize the local AI engine. This can take some time depending on your machine's performance.
It is sometimes necessary to wait between **2 and 5 minutes** during the first launch for everything to be operational.
## 3. Debugging Session
If the previous steps don't work, you might need to manually check what is blocking the engine.
Go to the [Debugging](/support/debug) section of this documentation.
Follow the instructions to launch the API manually and identify any error messages.
***
If the problem persists, feel free to join us on [Discord](https://discord.gg/WyBNCbZhBD) or contact us via email.
# Debugging
Source: https://docs.premierecopilot.com/support/debug
Troubleshoot and fix issues with the Première Copilot API.
If the extension is not responding, launch the API manually to identify the issue.
### 1. Copy the API Path
Choose the path corresponding to your installation:
**Mac:**
```bash theme={null}
/Library/Application Support/Adobe/CEP/extensions/PremiereGPTaescripts/js/libs/PremiereCopilotAPI/
```
**Windows:**
```bash theme={null}
C:\Program Files (x86)\Common Files\Adobe\CEP\extensions\PremiereGPTaescripts\js\libs\PremiereCopilotAPI\
```
**Mac:**
```bash theme={null}
/Library/Application Support/Adobe/CEP/extensions/PremiereGPTBeta/js/libs/PremiereCopilotAPI/
```
**Windows:**
```bash theme={null}
C:\Program Files (x86)\Common Files\Adobe\CEP\extensions\PremiereGPTBeta\js\libs\PremiereCopilotAPI\
```
**Mac:**
```bash theme={null}
/Library/Application Support/Blackmagic Design/DaVinci Resolve/Workflow Integration Plugins/DavinciGPT/js/libs/PremiereCopilotAPI/
```
**Windows:**
```bash theme={null}
C:\ProgramData\Blackmagic Design\DaVinci Resolve\Support\Workflow Integration Plugins\DavinciGPT\js\libs\PremiereCopilotAPI\
```
### 2. Access the Folder
* **Mac:** Open **Finder**, press `Cmd + Shift + G`, paste the path, and hit `Enter`.
* **Windows:** Paste the path into the **File Explorer** address bar and hit `Enter`.
### 3. Run and Report
Double-click **PremiereCopilot** (Mac) or **PremiereCopilot.exe** (Windows). A terminal window will open.
**If any error appears:**
* Take a screenshot of the terminal window.
* Send it **immediately** to **[admin@premierecopilot.com](mailto:admin@premierecopilot.com)** or in Discord.
If the window closes too fast to see the error, record a quick video of your screen to capture the message.
# Uninstalling Première Copilot
Source: https://docs.premierecopilot.com/support/uninstall
Completely remove the extension and all of its files from Windows or macOS.
Première Copilot installs in **two places only**:
1. The **extension folder** (the CEP extension + the local API engine), installed system-wide.
2. A **data folder** in your Documents (cache, transcriptions, generated files, presets).
Deleting both removes the software completely. Follow the steps for your operating system.
**Close Adobe Premiere Pro (and DaVinci Resolve) before you start.** Files that are in use cannot be deleted, and Premiere Pro must not be running when the extension folder is removed.
## Windows
### 1. Delete the extension folder
All extension files live under the Adobe CEP extensions folder in **Common Files**. Paste this path in the **File Explorer** address bar:
```bash theme={null}
C:\Program Files (x86)\Common Files\Adobe\CEP\extensions\
```
Delete the folder(s) below that exist on your machine — depending on which installer you used, only one of them will be present:
| Version | Folder to delete |
| --------------- | ----------------------------------------------------------------------------------------------------- |
| Beta / standard | `PremiereGPTBeta` |
| aescripts | `PremiereGPTaescripts` |
| aescripts GenAI | `PremiereGPTaescripts_genai` |
| Older versions | `PremiereCopilot` |
| DaVinci Resolve | `C:\ProgramData\Blackmagic Design\DaVinci Resolve\Support\Workflow Integration Plugins\davinciClaude` |
Deleting these folders requires **administrator rights**. Windows will ask you to confirm — click **Continue**.
The **aescripts** version also registers a classic uninstaller. You can remove it from **Settings > Apps > Installed apps > PremiereGPTaescripts** instead of deleting the folder by hand.
### 2. Delete the data folder
This folder holds the cache, thumbnails, transcriptions, generated audio and presets. Paste this in the File Explorer address bar (replace nothing — `%USERPROFILE%` resolves automatically):
```bash theme={null}
%USERPROFILE%\Documents\Adobe\Premiere Pro\Premiere Copilot
```
Delete the whole **Premiere Copilot** folder. It contains the following subfolders created at install time:
`audio_sync` · `image_generation` · `matplotlib_cache` · `music_analysis` · `rush_db` · `script` · `seq_preset` · `sfx` · `temp` · `thumbnails` · `transcription_analysis`
If you saved anything of your own in these folders (custom sequence presets in `seq_preset`, generated files in `image_generation` or `sfx`), back it up before deleting.
### 3. (Optional) Remove the debug registry key
The installer enables Adobe's unsigned-extension mode. It is shared by **all** CEP extensions, so only remove it if you use no other third-party Premiere Pro extension.
Open **Registry Editor** (`regedit`) and delete the `PlayerDebugMode` value in:
```bash theme={null}
HKEY_CURRENT_USER\Software\Adobe\CSXS.11
HKEY_CURRENT_USER\Software\Adobe\CSXS.12
```
Removing `PlayerDebugMode` will break any other unsigned extension you have installed. If in doubt, leave it as it is — it has no effect once Première Copilot is gone.
## macOS
### 1. Delete the extension folder
Open **Finder**, press `Cmd + Shift + G`, and paste:
```bash theme={null}
/Library/Application Support/Adobe/CEP/extensions/
```
Delete the folder(s) below that exist on your machine:
| Version | Folder to delete |
| --------------- | -------------------------------------------------------------------------------------------------------- |
| Beta / standard | `PremiereGPTBeta` |
| aescripts | `PremiereGPTaescripts` |
| aescripts GenAI | `PremiereGPTaescripts_genai` |
| Older versions | `PremiereCopilot` |
| DaVinci Resolve | `/Library/Application Support/Blackmagic Design/DaVinci Resolve/Workflow Integration Plugins/DavinciGPT` |
macOS will ask for your **administrator password** — this folder is outside your user account.
If you prefer the Terminal, this removes every possible variant in one go:
```bash theme={null}
sudo rm -rf "/Library/Application Support/Adobe/CEP/extensions/PremiereGPTBeta" "/Library/Application Support/Adobe/CEP/extensions/PremiereGPTaescripts" "/Library/Application Support/Adobe/CEP/extensions/PremiereGPTaescripts_genai" "/Library/Application Support/Adobe/CEP/extensions/PremiereCopilot"
```
### 2. Delete the data folder
Press `Cmd + Shift + G` in Finder and paste:
```bash theme={null}
~/Documents/Adobe/Premiere Pro/Premiere Copilot
```
Move the whole **Premiere Copilot** folder to the Trash. It contains the subfolders created at install time:
`audio_sync` · `image_generation` · `matplotlib_cache` · `music_analysis` · `rush_db` · `script` · `seq_preset` · `sfx` · `temp` · `thumbnails` · `transcription_analysis`
Or, in the Terminal:
```bash theme={null}
rm -rf ~/Documents/Adobe/"Premiere Pro"/"Premiere Copilot"
```
Back up anything of your own stored in these folders (custom presets in `seq_preset`, generated files in `image_generation` or `sfx`) before deleting.
### 3. (Optional) Forget the installer receipt
macOS keeps a record of the `.pkg` installation. It takes no meaningful space, but you can clear it:
```bash theme={null}
sudo pkgutil --forget com.trial17.premierecopilot
```
For the GenAI and DaVinci builds, the identifiers are `com.trial17.premierecopilot-genai` and `com.trial17.davinciclaude`.
## Verify the uninstall
Reopen Adobe Premiere Pro.
Go to **Window > Extensions**. **Première GPT Beta** should no longer be listed.
Both the CEP extension folder and `Documents/Adobe/Premiere Pro/Premiere Copilot` should be gone.
Uninstalling does **not** cancel your subscription. Manage or cancel it from your [account dashboard](https://www.premierecopilot.com/account).
***
Reinstalling later? Just run the installer again — it recreates both folders automatically. Note that the installer already deletes any previous version before installing, so you do **not** need to uninstall manually before an update.