How it works
Instead of transcribing Thai and then sending the text to a separate translator, Whisper does speech translation in one pass: it listens to the Thai audio and writes English. That avoids stacking two sets of errors and keeps timestamps aligned with the original speech, which is what you need for English subtitles.
- Add the Thai recording above. The language and output are already set.
- Choose Accurate for Thai.
- Review the English text, then export Word, PDF, SRT or VTT.
Common uses
- English subtitles for Thai videos you own.
- Understanding voice messages and voicemails in Thai.
- Research and reporting interviews conducted in Thai.
- Calls and meetings with Thai-speaking partners.
Need the original Thai text? Use Thai audio to text, and run both to compare line by line.
Writing Thai: what to expect in the transcript
Thai is written without spaces between words, so the app counts characters rather than words for reading speed and subtitle length. Punctuation comes out full width, as Thai readers expect. If you search the transcript, search for characters, not whole words.
Thai is a tonal language, so the same syllable can mean different things depending on pitch. Whisper uses the surrounding words to decide, which works well in normal sentences. Single words, place names and lists out of context are where to look first when you proofread.
If the speakers switch between Thai and another language, choose Thai manually instead of automatic detection. Automatic detection can be misled by a recording that opens in another language or with music.
Step by step: from recording to English text
- Add the Thai recording. Translate into English is preselected, so Whisper writes English directly while it listens.
- Choose Accurate or Best if you can. Translation benefits more from a larger model than transcription does.
- Keep the tab open while it works. English text appears line by line with timestamps that match the original speech.
- Review names and numbers. Speech translation aims for meaning, so check anything you will quote or rely on.
- For a transcript in the original language as well, run the same file again with Output set to Transcript in the same language.
- Export English subtitles as SRT or VTT, or a document as Word or PDF.
Which accuracy setting to choose for Thai
The speech model runs on your own device, so it is downloaded once and then saved in your browser. The app tells you the size before anything downloads, and it never downloads again unless you clear your browser data. For English, Balanced is usually enough. For most other languages, Accurate makes far fewer mistakes, and the app switches to it when you choose such a language.
| Setting | Model | One-time download | Best for |
|---|---|---|---|
| Fast | Whisper tiny | 64 MB | Quick drafts, phones, mobile data |
| Balanced | Whisper base | 136 MB | Clear speech and most everyday recordings |
| Accurate | Whisper small | 510 to 590 MB | Interviews, accents, names, most languages other than English |
| Best | Whisper large-v3-turbo | About 760 MB | Difficult audio; needs a computer with graphics acceleration |
On mobile data the app suggests Fast automatically. On a laptop with Wi-Fi, Balanced is the default and Accurate is worth the extra download if you transcribe Thai regularly. You can switch settings at any time; each model is downloaded only the first time you use it.
Fixing common problems
- The file will not open
- Most audio and video formats open directly. If a file is rejected, it usually uses a codec your browser cannot decode, such as some MKV or AVI files. Open it in a free converter or in the app that recorded it and save it as MP3, M4A or MP4. The file formats page lists what opens where.
- It is slower than expected
- Speed depends on your device and the accuracy setting. Chrome and Edge on a laptop with graphics acceleration are fastest. Plug in a laptop on battery, close heavy tabs, or choose a smaller setting. Phones work, but long files are faster on a computer.
- The wrong language was detected
- Automatic detection can be misled by music or a different language at the start. Choose Thai manually and run the file again.
- Repeated lines or text during silence
- Speech models can invent text during long silences or music. The app skips silent stretches and removes repeated lines, and Clean up audio helps further. If it still happens, try the Accurate setting.
- The browser ran out of memory
- Very long recordings on devices with little memory can hit the browser’s limit. Use Fast or Balanced, close other tabs, or split the recording into parts. A desktop or laptop handles several hours.
- The model download stopped
- Check your connection and try again. Model files that finished downloading are kept, so a second attempt is quicker. Once the model is saved, no connection is needed.
What happens to your Thai recording
Your browser reads the file from your device and runs the speech model locally. The audio, the video and the transcript are never sent to a server, so there is nothing for us, or anyone else, to store, train on or lose in a breach. Finished transcripts are saved only in your browser’s storage, where you can export or delete them in your library. The only thing that comes from the internet is the speech model itself, once. You can check this by turning off Wi-Fi after the first transcript: it keeps working.