Skip to main content
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. In the panel, it is the SRT file preset of Smart Subtitles. It is the text half of PremiereGPT’s caption tooling: if you want styled, burned-in captions on your timeline, pick a caption preset instead and see Smart Captions. Both share this exact editor. Works in Premiere Pro and DaVinci Resolve.

Quick Start

1

Pick SRT file

Open Smart Subtitles with your sequence open, and pick SRT file in the PRESET step.
2

Range & media

Pick Whole timeline or In / Out, then tick the media whose speech is transcribed. Media already transcribed by any PremiereGPT tool are reused for free.
3

Transcription

Set the spoken Language (or leave it on Auto), add an AI Context if needed, and click Transcribe. The chevron on its left lets you pick a different engine first.
4

Edit & export

Set Max Chars and Max Gap, then fix anything that’s wrong directly in the transcript: words, breaks, punctuation, casing.
5

Generate SRT

Click Generate SRT. The file lands in your export folder.
An SRT file can be made from up to 2 hours of timeline. Longer ranges are refused before any work starts.

Range & media

Choose what is transcribed: Whole timeline, or In / Out to limit the transcription and the subtitles to your In and Out points. Below the range, Media used for transcription lists the source files of the audio clips on your timeline (files under 5 seconds are hidden). Each one shows its length, its tracks and its state: By default, the media already transcribed are ticked and the new ones are not: tick the ones you want transcribed. Click the name of a transcribed media to read its first words. Under the list, PremiereGPT shows how many media are left to transcribe and about how many credits it will cost, or that everything ticked is already transcribed. Each media is transcribed once, in full, kept on this computer, then its words are placed back on the timeline wherever its clips are. Edit your sequence, change the range, or open another tool: the text follows your edit without a new transcription. When every ticked media is already transcribed, the Transcription step folds and the text arrives on its own.
With no media ticked, the mixed audio of the range is exported and transcribed instead.
Untick the media that carry no useful speech, like music or sound effects: they cost credits and add noise to the transcript.

Transcription

Language

The spoken language of your audio. Naming it explicitly beats Auto whenever you know it, especially on accented speech, technical vocabulary, or audio that starts with music or silence.

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:

PremiereGPT

Standard engine, fast and reliable. The default, and the right choice almost every time.

+ Advanced word precision

Re-syncs every word to the audio with forced alignment. Sharper timing, slightly slower, extra credits.

V2

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.
A media transcribed with a more precise engine is reused when you pick a less precise one. Picking a more precise engine transcribes again the media that were made with a lower one.

Edit & export

Caption limits

Max Chars by format:
  • 15 to 25: one short line at a time, social / vertical style.
  • 30 to 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).

Editing the transcript

The editor is the point of the tool. Everything below is instant and local, with no re-transcription.
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, next to Transcribe, 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

  • Range longer than 2 hours → refused up front. Use In / Out, 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. Untick the music media in Range & media.
  • 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: pick SRT file → tick the voice media → set the language → write ten lines of AI Context → standard engine → transcribe → Find & Replace the recurring errors → adjust Max Chars → Generate SRT.

Support

Questions or feedback? Join the Discord or write to admin@premierecopilot.com.