To test a free Hindi transcription tool, send a clip that mixes in English words and judge the result with a caution in mind. The announced word error rate for Hindi is 16.9, but independent tests report about 37, so Potok treats Hindi as uncertain.
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
- The 16.9 comes from the model's announcement, not from our measurement.
- 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.
- The transcript stays in Hindi and is not translated.
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
- Record mixed speech. Choose a clip where the speaker drops in English terms, as people often do.
- Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message or an audio file.
- Check which script each word has. See whether English words appear in Latin letters or in Devanagari, and whether that suits your use.
- Mark the spread of errors. Count the slips in the Hindi part and in the English part separately.
- Scale cautiously. Up to 2 GB is accepted, with Upload for large files. Export DOCX for a manual pass.
| 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 |
|---|---|---|
| Taking 16.9 at face value | Independent tests with other normalisation reported about 37. | Mention the spread and test your own clip. |
| Not splitting errors by language part | Mixed speech hides where the tool struggles. | Count Hindi and English slips apart. |
| Skipping the proofreading pass | The caution means real corrections. | Plan time to edit. |
| Using a noisy call recording first | Noise adds a second problem. | Start with a clean clip. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why does Hindi carry a caution?
Published numbers range widely, from 16.9 in the announcement to about 37 in independent tests.
Is the turbo figure relevant?
A third-party turbo average of 19.25 is one more data point, not a promise for your file.
Will English words be written in Latin letters?
It can vary from one passage to the next, so check a sample and decide whether the mix suits your use.
Which exports exist?
You can save the transcript as TXT, MD, DOCX, PDF, SRT or VTT, and DOCX is the easiest to edit by hand.
Is there an English version?
No. The transcript stays in the language of the recording.
How long should the test clip be?
A minute of natural speech is enough to see the pattern, as long as it contains both Hindi and the English words people mix in.
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