Pepys
9,438,517minutes transcribed

French Audio to Text

Drop in a French recording or paste a link – get a timestamped transcript that follows the speech, from Paris to Montréal to Dakar.

or paste a link
InstagramTikTokYouTubeFacebookSpotifyApple Podcasts

Accepts a French recording or video – MP3, M4A, WAV, MP4 and more, or a link · returns a clean, timestamped French transcript.

60 min free · no card required · we never train on your audio

PodcasterJournalistContent creatorResearcherStudent
Trusted by 100k+ usersRated 4.9 out of 5 by 100k+ users

How do I turn French audio into text?

Upload a French recording or paste a link, and Pepys turns the speech into clean, timestamped text in minutes – what the French call retranscription. It reads Metropolitan French along with Québécois, Belgian, Swiss and West African varieties, catches the liaisons and dropped syllables that throw off generic models, and auto-detects French among 99+ languages. Your first 60 minutes are free, no card.

How french audio to text works

01

Add your French audio

Upload an interview, a cours, a podcast or a voice note – or paste a link. No install, no format juggling.

02

Let it transcribe

Pepys writes the French speech out as timestamped text, accents and apostrophes intact.

03

Correct and export

Fix a word inline where you need to, then export to TXT, Markdown, DOCX, PDF, SRT, VTT, or JSON.

French isn't one accent on a map. Roughly 300 million people speak it, and the version in a Parisian podcast sounds nothing like a Montréal call-in show, a Brussels lecture, or an interview recorded in Abidjan. Pepys was tuned for that spread: Metropolitan French, Québécois, Belgian, Swiss and West African French all land as accurate, timestamped text you can search, quote and translate – not a flat best-guess that flattens the regional voice out of the recording.

The thing that wrecks ordinary speech models in French is how words run together. Liaisons glue the end of one word onto the start of the next, and casual speech swallows whole syllables ("je ne sais pas" collapses to "chais pas"), so the boundaries a model expects simply aren't there. Pepys is built to find them anyway. French is auto-detected among 99+ languages, your first 60 minutes are free, credits never expire, and we never train on your audio.

Clean paragraphs. No more um's and ah's.

The left is what Pepys hands back – logical paragraphs with the filler stripped out, punctuated and readable. The right is the raw, one-line-per-segment dump most transcribers leave you with.

reel-voiceover.mp4

um so yeah everyone keeps telling you to like lead with your best line right but uh honestly if you give away the whole answer in the first second you know there's basically no reason for anyone to keep watching so the hook isn't kind of the smartest thing you say it's like a loop you open that they need to close and um that's the part that actually keeps people around

Raw
BeforeAfter
  • Reads the full French range – Metropolitan, Québécois, Belgian, Swiss and West African – instead of one default accent

  • Handles liaisons and swallowed syllables, then lets you correct any word inline before export

  • Translate the finished French transcript into another language in a click, accents preserved

  • 99+ languages including French, auto-detected · we never train on your audio · credits never expire

Any language – 99+ detected automatically

Works with the platforms you live in.

Paste a link from YouTube, TikTok, Instagram, Facebook, Spotify, or Apple Podcasts – or drop in any audio or video file. We transcribe it once, then you export it however your workflow needs.

  • YouTubeYouTube
  • TikTokTikTok
  • InstagramInstagram
  • FacebookFacebook
  • SpotifySpotify
  • Apple PodcastsApple Podcasts
  • or any file

Export to any format

  • TXT
  • Markdown
  • DOCX
  • PDF
  • SRT
  • VTT
  • JSON

Timestamps, speaker labels, and subtitle timing carry through to every export.

French audio to text – questions, answered

How do I turn French audio into text?

Upload your French recording or paste a link on this page – the first 60 minutes are free, no card needed. Pepys writes it out as timestamped French text in a few minutes, ready to edit and export.

Does it understand Québécois and African French, not just Parisian?

Yes. Metropolitan French, Québécois, Belgian, Swiss and West African varieties all transcribe accurately. Where a regional term or proper noun slips through, you can fix it inline before exporting.

Why is French so hard to transcribe?

Spoken French chains words together with liaisons and drops syllables in casual speech, so the gaps between words that a model relies on often aren't audible. Pepys is built to track the speech through that and lets you tidy anything up by hand.

Does it get the accents and apostrophes right?

Yes – é, è, ç, ï, the œ ligature and the apostrophes from elision (l', d', qu') all render correctly, so the transcript reads as proper written French rather than stripped-down text.

Is my French audio private?

We never train AI on your audio or transcripts, and you can auto-delete your files once they're done.

More free tools

Keep reading

Don't just take our word for it.

Ask ChatGPT, Claude, or Perplexity what Pepys is and who it's for. One click, and your favorite AI does the homework.

French audio to text – free to start

Pay as you go – credits never expire, nothing to cancel. Or start free with 60 minutes, no card.