Hindi speech to text with Potok carries a caution. The model announcement gives a word error rate of 16.9, while independent tests with different text normalisation reported about 37, and a third-party turbo average was 19.25. Expect more mistakes than in recommended languages.
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
- Three published numbers, 16.9, about 37 and 19.25, disagree, so real quality depends on your audio and on the counting rules.
- Hindi speakers often mix English words into sentences, and those words may come out in either script.
- The 16.9 comes from the model's own announcement, which is published but not independent.
- Plan to proofread the whole transcript.
What a transcript looks like
[00:00] Speaker 1: चलिए बैठक शुरू करते हैं। पहले हम पिछले हफ़्ते के नतीजों की समीक्षा करेंगे, फिर अगले कदमों की योजना बनाएँगे।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 |
|---|---|---|---|
| Hindi (हिन्दी) | Use with care | word error rate 16.9% (large-v3, FLEURS) Whisper discussion, TheWhisper benchmark | Published tests show a higher error rate for this language. Check a short sample first and plan to proofread. The figure of 16.9 comes from the model's announcement; independent tests with a different text normalisation reported about 37, and a third-party turbo average was 19.25. Expect more mistakes than in the languages marked as recommended. |
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
- Decide which script matters to you. Mixed English words can appear in Latin or Devanagari letters, so decide what you will accept.
- Send a sample. Open @potok_now_bot in Telegram and attach one or two minutes of the speaker you need.
- Check mixed passages. Look at English words, brand names and numbers, where output is least predictable.
- Send the full file. The limit is 2 GB, and the Upload button handles large recordings.
- Export for editing. DOCX or TXT for corrections, SRT or VTT for captions.
| 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 |
|---|---|---|
| Using the best number as the expectation | The independent figure is more than twice as high. | Plan for the worse case. |
| Ignoring mixed-language speech | Sentences that blend Hindi and English are harder. | Check those passages first. |
| Skipping a sample | A flagged language varies a lot between speakers. | Sample first. |
| Quoting the numbers as ours | They are published by others. | Cite them as other people's tests. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why does Hindi have a caution?
The published figures disagree and independent tests found a higher error rate than the announcement.
What is the figure of about 37?
It comes from independent tests that used a different text normalisation, so it is not directly comparable.
Which script will English words use?
They can appear in either script, so check such words and fix them by hand if needed.
What is the file size limit?
Files up to 2 GB are accepted, and the Upload button helps with large ones.
Will the transcript be in English?
No. It stays in Hindi because the bot does not translate transcripts.
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
- Whisper speech recognition system (Wikipedia), Wikipedia · checked
- OpenAI Whisper discussion on large-v3 · 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