To test a free French transcription tool, use a clip full of words that sound alike and check the spelling of each. Potok cites published large-v3 word error rates of 5.3 to 6.31 for French, which are other people's tests and not measurements of your file.
Transcribe a recording
Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.
Open @potok_now_bot in Telegram
Files up to 2 GB · export to TXT, MD, DOCX, PDF, SRT and VTT · speaker labels and timestamps · about 30 languages
Key facts
- Published large-v3 results for French range from 5.3 to 6.31 in word error rate.
- These come from published tests by others, not from us.
- French has many words that sound the same but are spelled differently, so spelling is the best probe.
- The transcript stays in French and is not translated.
What a transcript looks like
[00:00] Speaker 1: Commençons la réunion. D'abord, nous passerons en revue les résultats de la semaine dernière, puis nous planifierons les prochaines étapes.Meaning in English: Let's start the meeting. First, we'll review last week's results, then plan the next steps.
Written by us to show the script and the layout of a transcript. It is not the output of the recognition engine.
Published quality
| Language | Verdict | Published result | Notes |
|---|---|---|---|
| French (Français) | Recommended | word error rate 5.3% (large-v3, FLEURS) Canary-1B-v2 paper, Whale paper, TheWhisper benchmark | Published tests show a low error rate for this language. Published large-v3 results range from 5.3 to 6.31. |
These numbers come from published tests by other people, not from tests by Potok. Your own audio, with its noise, accents and microphone, will differ.
How to do it
- Prepare sound-alike traps. Read a paragraph where several words share a sound but differ in spelling or agreement.
- Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message or an audio file.
- Check agreement. Look at plural and feminine endings, which are silent in speech and easy to lose.
- Check accents and apostrophes. Accent marks and elisions change words. See whether they are correct.
- Run the whole file. Up to 2 GB is accepted, with Upload in the mini app. Export TXT, DOCX or SRT.
| Feature | Details |
|---|---|
| Where it works | Telegram bot @potok_now_bot; large files go through the bot's mini app |
| File size | Up to 2 GB |
| Export | TXT, MD, DOCX, PDF, SRT, VTT |
| Speakers and time | Speaker labels and timestamps can be switched on |
| Languages | About 30 languages with good published results; a few more with warnings |
| Translation | The transcript is not translated into another language |
| Dictation | A separate Potok desktop app lets you dictate text into any program; it recognises Russian speech |
Common mistakes
| Mistake | What happens | Fix |
|---|---|---|
| Judging by how it sounds when read aloud | Silent endings make wrong text sound right. | Read the text, do not listen to it. |
| Overlooking accent marks | A missing accent turns one word into another. | Search for unmarked words. |
| Using one number as a verdict | The range runs from 5.3 to 6.31. | Quote the range. |
| Mixing in a speaker with strong background noise | It hides what the tool does well. | Test clean audio first. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How does French score?
Large-v3 results range from 5.3 to 6.31 in word error rate across published tests.
Why test with sound-alike words?
They reveal whether the tool uses context, which spelling depends on.
Can several speakers be labelled?
Yes. Speaker labels can be switched on and appear as numbers.
What is the size limit?
Files up to 2 GB are accepted, and the Upload button handles large ones.
Can I get English text?
No. The transcript stays in the language of the recording.
Does background music hurt the check?
It can. Music under speech makes errors harder to trace, so cut a clip where people talk over a quiet background.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
- Word error rate (Wikipedia), Wikipedia · checked
- Canary-1B-v2 paper, Table 11 (Whisper large-v3 on FLEURS) · checked
- Whale paper, Table 5 (Whisper large-v3 on FLEURS) · checked
- TheWhisper benchmark (turbo, average over FLEURS, MLS, Common Voice) · checked
Try it on your own recording
Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.
Open @potok_now_bot in Telegram