To test a free English transcription tool, pick a short clip in the accent you actually need and read the text against the audio. Potok cites published large-v3 word error rates of 4.0 to 4.25 for English, from other people's tests rather than ours.
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 English range from 4.0 to 4.25 in word error rate.
- The turbo variant averages 4.80 in a third-party test.
- English is the best-covered language in published tests, yet accents and jargon still cause trouble.
- The transcript stays in English and is not translated.
What a transcript looks like
[00:00] Speaker 1: Let's start the meeting. First, we'll review last week's results, then plan the next steps.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 |
|---|---|---|---|
| English | Recommended | word error rate 4% (large-v3, FLEURS) Canary-1B-v2 paper, Whale paper | Published tests show a low error rate for this language. Published large-v3 results range from 4.0 to 4.25; the turbo variant averages 4.80 in a third-party test. |
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
- Choose the accent that matters. Pick a minute of speech from the kind of speaker you will really transcribe, not from a news reader.
- Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message, an audio file or a video.
- Hunt for jargon. Include product names, acronyms and surnames. They are where a good-looking transcript fails.
- Compare homophones. Check words that sound alike, and see whether context picked the right one.
- Scale to the whole recording. Up to 2 GB is accepted, with Upload in the mini app for the biggest files. Export TXT, DOCX, SRT or VTT.
| 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 |
|---|---|---|
| Testing with a studio-quality voice only | It flatters every tool and says nothing about your speakers. | Add a clip with a regional accent or a speaker on a phone line. |
| Skipping acronyms | They are rarely written the way the field writes them. | Put several in the clip and check each one. |
| Treating a range as one number | Results span 4.0 to 4.25 across tests. | Quote the range and name the model. |
| Comparing at different volumes | Quiet audio hurts one tool more than another. | Use the same file everywhere. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How does English score in published tests?
Large-v3 shows word error rates from 4.0 to 4.25, and a third-party turbo average of 4.80.
Do accents change the result?
They can. The published figures do not break out accents, so test the one you need.
Can I send a YouTube link?
Yes. Links are accepted alongside voice messages, audio files and video.
Can I get timestamps?
Yes. Switch them on before sending, and every passage then carries a time you can use to jump back into the audio.
Can the text come out in another language?
No. The transcript stays in the language of the recording.
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
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