To convert English audio to text, send the file to the Potok bot on Telegram. Published tests of others on large-v3, not our measurements, give a word error rate of 4, with reported results from 4.0 to 4.25. Files up to 2 GB work, and the text stays in English.
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
- A third-party test of the faster turbo variant averages 4.80, so the model choice moves the number a little.
- English is the best-covered language in the published tests, so its figure is the most stable.
- Accent, noise and crosstalk move your own result more than the model name does.
- Short results arrive in the chat and long ones as a file.
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
- Open the bot. Open @potok_now_bot in Telegram.
- Attach your recording. Audio, video, a voice note or a YouTube link; files up to 2 GB. Press Upload for larger ones.
- Pick speaker labels. Switch them on for meetings and interviews so each line has a number.
- Proofread proper nouns. Brand names, surnames and acronyms are the usual misses, even in English.
- Listen to one tricky passage. Pick a fast or noisy stretch and compare it with the text. It tells you how much of the rest needs a close read.
- Export. Choose TXT, MD, DOCX, PDF, 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 |
|---|---|---|
| Assuming clean text because the rate is low | A rate of 4 still means errors in a long file. | Proofread anything that will be published. |
| Mixing in another language | Foreign phrases are often spelled by sound. | Fix them by hand. |
| Recording on speakerphone | Echo hurts every recogniser. | Use a headset or place the phone near the speaker. |
| Sending music with speech | Background music masks consonants. | Send the speech track alone if you have it. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How accurate is English?
Published results are about 4 word error rate on large-v3, among the best, but they are tests of others.
Does the accent matter?
Yes. Strong accents and noisy rooms raise errors, even for English.
Can I get subtitles?
Yes, export SRT or VTT with timestamps switched on.
What is the file limit?
2 GB per file, and the Upload button of the mini app handles the biggest ones.
Will it correct my grammar?
No. It writes what was said, so spoken mistakes appear in the text.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Word error rate (Wikipedia), Wikipedia · checked
- FLEURS speech dataset (Google, Hugging Face), Hugging Face · 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