To convert Hindi audio to text, send the file to the Potok bot on Telegram, with a caution. Published figures of others vary: 16.9 word error rate from the large-v3 announcement and about 37 in independent tests with different normalisation. Expect more mistakes than in recommended languages. Files up to 2 GB work.
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 average for the faster turbo variant was 19.25, which sits between the two figures.
- Text normalisation changes the score a lot, so compare figures only from the same test.
- Hindi is written in the Devanagari script, so your editor needs a Unicode font.
- Everyday Hindi speech often mixes in English words.
- A video or YouTube link is read like audio, so you can transcribe a talk without extracting the sound first.
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
- Plan a review. Treat the output as a draft, because published results span a wide range.
- Open the bot. Open @potok_now_bot in Telegram.
- Send the file. Audio, video or a YouTube link, up to 2 GB. Use Upload for big files.
- Check the mixed English words. Look for English terms inside Hindi lines and see whether they were written in Devanagari or Latin letters.
- Check names and numbers. Personal names and counted figures are the likeliest misses, so confirm them against the recording.
- Export. DOCX or TXT for editing, 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 |
|---|---|---|
| Quoting only the 16.9 | Independent tests were worse. | Give the whole range. |
| Using a font without Devanagari | The text shows as boxes. | Use a Unicode font. |
| Skipping the review | Errors are likelier here. | Proofread against the audio. |
| Comparing figures from different tests | Normalisation differs. | Compare like with like. |
| Expecting every English word in Latin letters | The recogniser may write them in Devanagari instead. | Decide which style you want and edit to match. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why does the Hindi page carry a caution?
Published results range widely, from 16.9 to about 37, so the output needs careful checking.
Which figure is the best case?
16.9, which comes from the model's announcement and is not our own measurement or a neutral test.
What is the size limit?
2 GB per file, with the Upload button for large ones.
Is the text translated?
No. The text stays in Hindi, the language of the recording you sent to the bot.
Can I send a video?
Yes, a video is read like audio, within the 2 GB limit of the bot.
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
- 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