Thai comes with a caution at Potok. The published character error rate for the earlier large-v2 model is 11.5, and OpenAI itself names Thai as a language where the faster turbo variant gets worse. Text is returned in Thai, with no spaces between words. Files up to 2 GB are accepted.
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 11.5 is a character error rate, not a word rate, because Thai is written without spaces between words; it is a published figure, not our measurement.
- A third-party run of the turbo variant gave about 13.4, so the choice of model matters.
- Spaces in Thai text mark phrases or sentences, not single words.
- A reader needs to check names and numbers against the audio.
What a transcript looks like
[00:00] Speaker 1: เรามาเริ่มประชุมกันเลย ก่อนอื่นเราจะทบทวนผลลัพธ์ของสัปดาห์ที่แล้ว จากนั้นจะวางแผนขั้นตอนต่อไปMeaning 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 |
|---|---|---|---|
| Thai (ไทย) | Use with care | character error rate 11.5% (large-v2, FLEURS) Whisper paper, Whale paper, Whisper turbo discussion | Published tests show a higher error rate for this language. Check a short sample first and plan to proofread. Thai is written without spaces, so quality is reported as a character error rate. OpenAI itself names Thai as a language where the faster turbo variant gets worse, and a third-party turbo run gave about 13.4. |
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
- Expect to edit. Treat the first output as a draft that needs a proofreading pass.
- Send a sample. Message @potok_now_bot with a short Thai clip and look at the lines.
- Send the full file. Up to 2 GB works, and the Upload button of the mini app helps with large video.
- Turn on timestamps. With no spaces, long lines are hard to scan, so times give you anchors.
- Prepare subtitles with care. Export SRT or VTT and set line breaks by hand.
- Export documents. TXT, MD, DOCX or PDF.
| 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 |
|---|---|---|
| Comparing 11.5 with word error rates | The units differ, so the comparison misleads. | Compare character rates with character rates. |
| Using a text editor that breaks lines by spaces | Thai lines wrap unpredictably. | Use an editor with Thai line breaking. |
| Skipping the review for a speedy workflow | A cautioned language leaves visible errors. | Reserve time to proofread. |
| Assuming speaker names are filled in | Labels are numbers only. | Add names yourself. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why does Thai carry a caution?
The published results are weaker than for the recommended languages, and OpenAI notes Thai gets worse in the turbo variant.
Why a character error rate?
Thai has no spaces between words, so counting characters is the fairer measure.
Can I still use it?
Yes, for drafts, notes and search, provided someone reads the text before it is relied on.
Can I make captions?
Yes, export SRT or VTT, then check the line breaks.
Does it translate Thai?
No. The text stays in Thai, and the bot does not offer another language.
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
- Whisper paper, Table 13 (large-v2 on FLEURS) · checked
- Whale paper, Table 5 (Whisper large-v3 on FLEURS) · checked
- OpenAI Whisper discussion on the turbo model · 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