Free Thai transcription calls for caution and a short clip test. Published tests of others put the character error rate at 11.5 on the earlier large-v2 model, and a third-party turbo run gave about 13.4. Potok users should read every Thai transcript against the 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
- Caution: Thai is flagged because OpenAI itself names it as a language where the faster turbo variant gets worse.
- Thai is written without spaces, so quality is reported per character, not per word.
- The 11.5 is from large-v2 and was made by others; it is not our measurement.
- Sentence breaks are not marked by spaces, so the text may run on.
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
- Choose a clear clip first. Start with a slow, close-microphone sample, and move to a messier one later.
- Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message, an audio file or a video.
- Count characters. Mark wrong, missing or extra characters rather than words, and divide by the length of the text.
- Check tone and vowel marks. Compare marks on a handful of words against the audio, since a wrong mark changes the word.
- Insert breaks. If the result runs together, add spaces where sentences end before you share it. Files up to 2 GB are accepted for longer recordings.
| 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 |
|---|---|---|
| Trusting the text as it stands | Thai is a flagged language here, so slips are more likely. | Plan a complete read-through. |
| Counting words | No spaces mean the count is meaningless. | Use characters. |
| Using a turbo-only comparison | It can look worse for Thai. | Look at the figures for the model actually used. |
| Skipping the noisy clip | Quality can fall faster in noise. | Test under real conditions. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why does Thai carry a caution?
Published figures are weaker than for the recommended languages, so a careful read is part of the job.
What are the 11.5 and 13.4?
11.5 is a character error rate for large-v2; about 13.4 is a third-party turbo result.
Why characters, not words?
Thai has no spaces between words, so characters are counted.
Can I get the text in English?
No. The transcript stays in the language of the recording.
How large a file can I send?
Files up to 2 GB are accepted, and a long result arrives as a file.
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