Skip to content
Speech to text, built for real audio

French audio to text converter

PyAI is free to start and works as a French transcript generator: upload or record audio and read the text back in seconds. Convert French audio into clean text with PyAI Hear. One endpoint accepts a file or a live stream and returns a transcript with timestamps, whether the voice is from France, Quebec or West Africa.

France, Quebec and West African accentsPhone and studio audiowhisper-1 compatible$0.001/min

Explore first. Get a sandbox key when you are ready to build.

PyAI in motionInteractive example
Sample: a 14 second French delivery coordination call
0:00LivreurBonjour, je suis en bas de l'immeuble avec votre colis.
0:03ClientAh merci, l'ascenseur est en panne. Je descends tout de suite.
0:08LivreurPas de souci, je vous attends devant la porte vitrée.
0:12ClientParfait, j'arrive.
Drop an audio file, or record a clip

Try it free: 3 transcriptions, up to 3 minutes each, no account needed. After that, create a free account with $50 in credit.

  1. 1Upload or recordA file or a mic clip, up to 3 minutes
  2. 2Hear transcribesSpeech recognition tuned for real audio
  3. 3Read it hereThe transcript shows right on this page

A sample of how Hear returns French transcripts, with per segment timestamps and speaker labels.

French speech to text, built on PyAI Hear

French speech to text turns spoken French into written text your software can store, search and act on. PyAI Hear is the engine behind it, the same recognizer that drives live phone agents on PyAI. Hear reads clear studio audio and rough 8 kHz phone lines, follows French from France, Canada and West Africa, and returns text as plain, JSON or timestamped output. You call it from your own code and the audio never leaves your flow. Drop in a recording and PyAI works as a French voice to text tool, or call the same endpoint to transcribe French audio to text in bulk. The same audio to text generator serves a single upload or thousands of calls a day. PyAI works as a free French speech to text generator, so a saved file or a quick recording turns into text you can edit, search and reuse.

Key takeaways

  • Price: $0.001/min, billed by the whole minute.
  • Accents: metropolitan French from France, Quebec French from Canada, and West African French from countries like Senegal and Ivory Coast all run on one model, so a call that mixes them still returns one clean transcript with no dialect chosen up front.
  • Speed: first partial lands near 200 ms, long files run 92 to 247 times real time.
  • Accuracy: word error rate is 1.59% on clean audio and 4.76% on real 8 kHz phone audio, PyAI's own benchmark numbers measured on English and reported as industry parity, not a lead.
  • Free tests: $50 credit with no credit card, and sandbox keys never bill, so you can try French audio before paying anything.
  • Drop in: a whisper-1 client reaches Hear by changing the base URL, and single files up to 25 MB work in one call.

How French transcription works

You send French audio to one endpoint and get text back. The same engine runs as a file call, a live stream, or a background job.

Send the audio

Post a French file to the transcription endpoint, or open a WebSocket and stream PCM16 frames for a live delivery call, hotline or meeting.

Hear recognizes it

The engine runs in one region, detects speaker turns, and commits each final line once a speaker finishes, so partial text firms up as more audio arrives.

Formatting is applied

Smart formatting, dictation and filler removal clean the text, and numbers, dates and currency are written the way a French reader expects.

You get text back

Plain text, JSON, or verbose JSON with per segment timestamps and speaker turns, ready for notes, captions or search.

What Hear handles in French

French brings its own accents, numbers and names. Here is how Hear deals with them.

France, Quebec and Africa

Parisian French, Quebec French with its own vowels and expressions, and West African French share one model. You do not pick a region first, and a mixed call still resolves into a single transcript.

Phone audio

Hear is tuned for 8 kHz phone lines, the hard case. PyAI measured 4.76% word error rate on noisy, accented call audio in English, so test a few French calls.

Liaison and elision

Liaison, elision and fast connected speech run French words together. PyAI has no French accuracy figure, so check a few natural recordings for word boundaries.

Numbers and names

Amounts, dates and reference numbers are written in digits, and up to 5 custom vocabulary terms teach it the names, places and product words your business leans on.

Overlap and turns

A turn detector records who spoke when, so two voices on top of each other return as separate labeled segments rather than one run on line.

Long recordings

A long interview is split into overlapping chunks, transcribed in parallel and stitched back together, which is how throughput reaches 92 to 247 times real time.

Accuracy and speed

Hear is at industry parity for accuracy, held on the hard case of real phone audio. The figures below are PyAI's own measurements on English speech, not a per language claim.

1.59%Word error rate, clean audio
4.76%Word error rate, 8 kHz phone and noisy
~200 msTo the first partial transcript
92 to 247xReal time, batch throughput

What you can transcribe in French

The same French endpoint feeds notes, captions, search and analytics.

Call transcription

Log every French support or sales call as searchable text, then route it to quality review, coaching or a CRM note.

Delivery and field calls

Capture delivery, dispatch and field coordination calls as text, so addresses, times and handoffs are written down instead of half remembered.

Meeting notes

Stream a French meeting live and get a running transcript with speaker labels, so action items are caught without a dedicated note taker.

Captions and subtitles

Generate French captions for video with per segment timestamps that drop straight into an SRT or VTT file.

Interviews and podcasts

Transcribe long French audio as a background job and get timestamped text back to quote, clip or index.

Voice search

Send short French clips and act on the text, so a user can speak a query or command inside your product.

Formats, limits and output

What a French transcription request takes and returns
InputAudio file up to 25 MB for a single file call, or a live PCM16 stream over WebSocket for real time. OpenAI compatible, so a whisper-1 client works unchanged.
OutputPlain text, JSON, or verbose JSON with per segment timestamps. Smart formatting, dictation and filler removal are applied on the way out.
ModesSync file call for short clips, live streaming for calls and meetings, and background jobs for long recordings that run 92 to 247 times real time.
TuningSet the language to French, add numerals handling, and load up to 5 custom vocabulary terms so names and product words land right.
Billing$0.001/min of audio, rounded to the whole minute. An empty transcript costs nothing, and a busy engine returns a retry, not a charge.

Call French speech to text from your own code

Hear follows the OpenAI transcription shape, so most French code reaches PyAI by changing the base URL. Full docs live at PyAI SDKs.

SDK

From a server, the SDK posts a French file or opens a stream and returns the transcript in a few lines. The SDK speaks the whisper-1 shape, so transcription code you already run moves across by swapping the base URL.

MCP

With the MCP server, an agent can transcribe a French recording by itself as one step in a flow, for example turning a delivery call into a dispatch note, without you wiring the API by hand.

CLI

From the terminal, the CLI takes a French audio file or a folder and writes out text or timestamped JSON, useful when a backlog of recordings needs clearing in one pass.

Where Hear fits

PyAI is voice infrastructure. Hear, Speak and Omni run together in one stack and one region, so recognition, reasoning and reply keep a single session instead of hopping between vendors. Hear is not a consumer dictation app, and PyAI does not resell someone else's recognizer. Hear is the French transcription engine you call from your own product, on your own calls and files. See the published numbers on PyAI benchmarks.

Get a sandbox key → $50 free credit. No credit card. Sandbox keys never bill.

French speech to text FAQ

How accurate is French speech to text on Hear?

Hear measures 1.59% word error rate on clean audio and 4.76% on real 8 kHz phone audio. Both figures are PyAI's own benchmark figures, taken on English and at industry parity, so they describe the engine as a whole rather than any single French accent or recording quality.

Does it cover France, Quebec and African French?

Yes. Metropolitan French, Quebec French and West African French all run on one model, so you do not select a region in advance. Up to 5 custom vocabulary terms help with names and product words that matter in your audio.

How much does it cost to transcribe French audio?

Hear charges $0.001/min of audio, rounded to the whole minute, and an empty transcript is free. A new account starts with $50 of credit and no credit card, enough for a large batch of test audio before you pay anything.

Will my whisper-1 code still work?

Yes. Hear follows the OpenAI transcription format, so a client built for whisper-1 works once it points at the PyAI base URL. You keep the same request shape and receive text, JSON or verbose JSON with timestamps back as usual.

Does Hear handle live French or only files?

Both. A single file call suits clips up to 25 MB, a WebSocket stream handles live calls and meetings with partials near 200 ms, and a background job processes long recordings at 92 to 247 times real time. Both paths bill at the same per minute rate.

Prices checked November 2026. Hear figures from pyai.com/benchmarks.

Start transcribing with PyAI Hear

Spin up a sandbox key and turn calls, meetings and recordings into clean text in minutes. No credit card, and $50 in free credit.

Get a sandbox key →