Chinese speech to text with Potok covers Mandarin and is marked as recommended. Published tests of large-v3 report a character error rate of 7.8, down from 14.7 for the earlier large-v2 model. Both are third-party figures, not our measurements, and results depend on your audio.
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 older large-v2 model scored 14.7 in the same kind of test, so the newer model roughly halves the published error.
- Chinese is written without spaces, so results are quoted per character.
- A character error rate counts wrong, missing or extra characters against a reference text.
- This page speaks about Mandarin; other Chinese varieties are not covered by these figures.
What a transcript looks like
[00:00] Speaker 1: 我们开始开会吧。首先回顾上周的结果，然后规划下一步。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 |
|---|---|---|---|
| Chinese (Mandarin) (中文（普通话）) | Recommended | character error rate 7.8% (large-v3, FLEURS) Whale paper, Whisper paper | Published tests show a low error rate for this language. Chinese is written without spaces, so quality is reported as a character error rate. The earlier large-v2 model scored 14.7. |
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
- Confirm it is Mandarin. Published results here describe Mandarin. A recording in another variety needs its own test.
- Send the file. Open @potok_now_bot and attach audio, video or a voice message.
- Use Upload for long ones. The bot accepts up to 2 GB; the Upload button of its mini app handles the big files.
- Scan numbers and names. Digits, product names and personal names are the likeliest places for a wrong character.
- Export. TXT or DOCX for notes, SRT or VTT for subtitles.
| 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 |
|---|---|---|
| Applying Mandarin figures to another variety | The numbers were not measured for it. | Check a clip first. |
| Comparing 7.8 with a word error rate | The units differ, so the comparison misleads. | Compare characters with characters. |
| Quoting 14.7 as current | That is the older model. | Quote 7.8 for large-v3 and label it published. |
| Searching the output for word gaps | There are no spaces between words. | Search for the character string instead. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Does this cover Cantonese too?
No. Cantonese has its own page and its own published numbers.
What does 7.8 mean?
It is a character error rate from published tests, roughly 7.8 wrong characters in every 100.
Is the output simplified or traditional characters?
We have no published data on that, so check a sample if the script matters to you.
Can I send a video call recording?
Yes. Video, audio and voice messages are accepted up to 2 GB per file.
Will the text be put into English?
No. It stays Chinese; 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
- Whale paper, Table 5 (Whisper large-v3 on FLEURS) · checked
- Whisper paper, Table 13 (large-v2 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