Transcribe narration and voiceover. As text and SRT captions, with every word timed.
A voiceover transcript turns the read into text with every word timed, ready to check against the script and become captions. Upload the narration audio (MP3, WAV, M4A) or the cut video. We return the text, a synced SRT file, chapters and MP3 excerpts. You check what was recorded by reading it, not by listening to the whole session again.
Updated
Where narration transcripts eat your time. And what comes out ready.
Captions that match the voice
We time every word of the read, so captions land on the narrator's rhythm. Export SRT with the broadcast, Netflix or YouTube preset and pick your project's frame rate. Cutting in Final Cut? Captions also come out as FCPXML. Fix any word in the text before exporting and it is fixed in the file. As a reading-speed reference, TV and streaming usually sit between 17 and 20 characters per second for adult audiences, with up to 42 characters per line.
Checking the read against the script
Did the narrator swap a word? Skip a line in paragraph four? With the transcript next to the script, review becomes reading. Search for a line to see exactly when it was said. For client approval, export the text as PDF or TXT, so they can read what was recorded without opening an audio file.
Multiple takes of every paragraph
Studios usually deliver two or three takes of each section in one file. In the transcript, the takes sit one under the other, each with its own timestamp. Search the line, listen to just those reads and mark the best one as a favorite. Per-line emotions help you compare delivery without replaying the whole session.
Getting your picks onto the timeline
On Studio, Agency and the trial, export the sequence of favorites already cut to Premiere Pro or DaVinci Resolve (.xml) or Final Cut Pro (.fcpxml). Set handles and the gap between excerpts before exporting. Your chosen takes land in order, ready for picture.
Excerpts for approval and teasers
Download just the paragraph that needs sign-off as an MP3 and send it to the client. On Studio and Agency, the hooks tab lists the strongest lines with an impact score, and the script builder assembles a shorter cut at the length you ask for, from 3 minutes up, using lines from the narration itself. That is your teaser's starting point.
Versions in other languages
On Studio and Agency, captions and text can be translated into 9 languages: Spanish, Portuguese, French, German, Italian, Japanese, Korean, Chinese and English. The voice stays the original; what we translate is the captions. If the voiceover will be re-recorded in another language, the translated text is a starting point for that script too.
How to transcribe a voiceover and make captions in 3 steps
- 01
Upload the voiceover
Audio or video, as MP3, WAV, M4A, AAC, MP4, MOV and more. Multiple takes can go in the same file.
- 02
We transcribe it word by word
Text with every word timed, chapters, narrator kept apart from interviewees and the emotion behind each line.
- 03
Take it into the edit
SRT with the right preset, a sequence of your best takes for the editor, MP3 excerpts and a PDF of the text for approval.
A documentary voiceover, from the booth to the timeline
An editor gets a 42-minute WAV from the recording studio: the full narration for an 18-minute documentary, with two or three takes of every paragraph. He uploads it as is. Within minutes, the transcript shows each take as text, with every word timed.
He searches for "Forty years later" and finds all three reads, one under the other. He listens to just those three, marks the best as a favorite and moves to the next paragraph. Along the way he fixes the town's name, which the narrator said correctly but the text spelled differently.
On Studio, he exports the sequence of favorites to Premiere Pro as .xml, with short handles between excerpts. The chosen takes land on the timeline in script order. The PDF of the text goes to the director for approval, along with an MP3 of the opening.
Once picture is locked, he uploads the final 18-minute mix, which uses another 18 minutes of quota, and downloads the SRT with the broadcast preset at the project's frame rate. The festival version gets captions translated into Spanish and French.
What you get from every narration transcript
| Output | Format | What it is for |
|---|---|---|
| Narration text | TXT or PDF | Checking against the script and approval |
| Synced captions | SRT (broadcast, Netflix, YouTube) or FCPXML | Timeline and publishing |
| Sequence of best takes | .xml or .fcpxml (Studio, Agency and trial) | Premiere, DaVinci and Final Cut |
| Excerpts | MP3 | Client approval and teasers |
| Chapters | Timestamped list | Navigating the narration |
| Hooks and short script | Scored lines and a 3 to 120 min script (Studio and Agency) | Teasers and cutdowns |
| Translated captions | 9 languages (Studio and Agency) | International versions |
“It used to take me days to finish the story of a script; now I can write it in less than an hour.”
More than voiceover transcripts. The same text feeds other deliverables.
See also
Voiceovers add up to a few hours a month and fit Pro. Editor sequences and hooks come with Studio.
Compare plans →- Transcription with speakers and chapters
- Emotions in every line
- Automatic clips with animated captions
- Remove pauses and filler words
- Downloads without watermark
See all features
- Manual clips, trimmed word by word
- Saved clip templates for the next ones
- Emotion filter
- Favorite and export lines in bulk
- Export as TXT, PDF, SRT, MP3 and MP4
- Everything in Pro
- Scored hooks and scripts
- Timeline for Premiere, DaVinci and Final Cut
- Translation and speaker names
- Your logo and your font on clips
- Connector for ChatGPT, Claude and Gemini
- Team: each person at R$ 29/month, with 3 more hours
See all features
- Moments inside each chapter
- Diagrams: mind map, flow and timeline
- Image and font library for clips
- Projects to organize by client
- Support
- Everything in Studio
- FilmScribe Plugin for DaVinci Resolve Studio (beta)
- Team with 2 people included
- Priority support
- Extra hours at R$ 7
3-day trial or 1 hour of material. See the result on your own recording before adding a card.
Frequently asked questions
How do I turn narration into synced captions?
Upload the audio or video with the narration. We transcribe it with every word timed, and you export an SRT with the broadcast, Netflix or YouTube preset at your project's frame rate. For Final Cut, captions also come out as FCPXML.
Can I export narration as SRT?
Yes. The SRT comes out with the timing of every line, ready to import into Premiere Pro, DaVinci Resolve or any player. Review the text first: whatever you fix in the transcript is fixed in the captions. You can also download the plain text as TXT or PDF.
Can I translate the narration?
Yes, on Studio and Agency: captions and text go into 9 languages, including Spanish, French and German. The voice stays the original: we don't dub. The translated text works as captions for international audiences and as a base for re-recording the voiceover in another language.
Can I upload just the voiceover audio?
Yes. From audio you get the transcript, speakers, chapters, emotions, SRT captions and MP3 excerpts and, on Studio and Agency, hooks and the editor sequence. Video clips, burned-in captions and reframing need video: upload the cut version later if you want those.
How do I find the best take without listening to everything?
Search the line in the transcript and every take of it shows up, each with its own timestamp. Listen to just those and mark the best as a favorite. On Studio, Agency and the trial, the sequence of favorites goes straight to Premiere, DaVinci or Final Cut.
Does it work with narration in other languages?
Yes. Transcription works in 90+ languages, with automatic language detection. A Spanish voiceover is transcribed in Spanish, with every word timed, and on Studio and Agency it can get English captions or captions in any of the 9 translation languages.