French transcription
French audio and video to text
Drop in a French recording and read it back as text, one timestamped line at a time. Select French as the language for the most dependable result.
What French audio tends to need checked
French has many words that sound alike and are spelt differently, so a transcript can be phonetically right and grammatically wrong. Proof-read agreement, homophones and accented characters, and fix them in the editor.
French from different places
Metropolitan, Canadian, Belgian and African French differ in accent and vocabulary. Clear audio matters more than the variety, but expect more errors on fast, informal or overlapping speech.
Typical uses
Interviews and research recordings, lectures, business calls with French partners, and French captions for a video you made.
Which model works best for French
French is one of the languages Whisper-family models have seen the most speech in, so the small model can give a reasonable first draft from clear audio. That is not a promise of accuracy: it still slips on names, numbers, jargon and overlapping or noisy speech, so proof-read anything you will publish or rely on.
On tryscriptorium.com the no-account preview and regular accounts run the small model (the larger medium and large-v3 models run when you self-host Scriptorium).
French has a large amount of training speech behind it. The usual errors are homophones and agreement, which look right on a quick read, so listen to the audio for any sentence you plan to quote.
Subtitles and captions in French
French subtitles are usually two lines of about 37 to 42 characters. Check the apostrophes and the spacing before : ; ? ! after you edit, since typing conventions differ between editors.
The uploader is set to French
The upload box on this page transcribes as French, so the recogniser does not have to guess the language from the first seconds. If the recording is in another language or switches languages, use Audio to text, which detects the language automatically. Automatic transcription is a draft and no accuracy figure is promised: check names, numbers and anything you will rely on.
How it works
Add a recording
Drop in a video or audio file, choose one from your device, or record from the microphone. Nothing to install.
It transcribes
Speech becomes timestamped text, with speaker labels when more than one person talks.
Read, fix, export
Click any line to correct it, then download TXT, subtitles, Markdown, JSON or CSV.
Related
- Interview transcription Research and press interviews
- Lecture transcription Cours and conferences
- Audio to SRT French subtitles for a video
- Transcribe an interview Workflow for recorded interviews
- How to add subtitles to a video Using the SRT you export
- Spanish transcription A related language, Spanish.
- Portuguese transcription A related language, Portuguese.
- Italian transcription A related language, Italian.
- All transcription languages Every supported language and how well it is covered.
- Pricing Free limits and paid plans.
Questions
Can I transcribe French and keep the accents?
Can I get French subtitles for a video?
Which file types can I upload?
Is it free?
Want your transcripts saved and longer files? Create a free account · See pricing · All use cases
Try it with your file
No account needed for a first transcript.