Skip to main content
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

1

Choose the range

Open the long-form sequence, then pick Whole timeline or In / Out to analyze only the part between your In and Out points.
2

Choose the format

Ready-made clips finds self-contained passages. Assembled reels builds each reel from several moments of the video.
3

Set the analysis

Choose how many clips or reels you want, the target durations and the signals, and add an optional brief.
4

Analyze and review

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.
5

Create the clips

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: 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

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:
1

Captions source

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.
2

Transcription settings

The same settings as Subtitles Pro: context and language for a new transcription, then caption length, gaps and punctuation.
3

Caption engine (Premiere Pro only)

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.
4

Design

The Smart Captions design panel, with a preview using words from your selected results.
5

Create Virals

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.