Why are there no spaces between words?

Because written Thai does not use them; spaces separate phrases. The output follows the normal convention, so it reads correctly to Thai readers.

Because the smaller models make many more mistakes in Thai. Best is slower but produces text that can be edited rather than retyped.

Does it handle Isan or southern speech?

Central Thai is most accurate. Strong regional speech loses accuracy, as dialects do in every language.

Will the Best model run on my phone?

Sometimes. Best needs more memory and time than the other models, so an older phone or a laptop with little RAM may struggle. If it stalls, switch to Accurate, which still handles clear Thai speech reasonably.

Can I save the Thai transcript as a file?

Yes. Download it as a TXT file in Thai script, or copy the text straight into a document or messaging app. For video, the subtitle exports include timestamps alongside the Thai text.

Transcribe Thai Audio to Text — Free, No Upload

Turn Thai audio or video into Thai-script text in your browser. 100% free, no per-minute limit, no signup — nothing is uploaded. Opens with the most accurate model.

Model

Spoken

Output

Timestamps [0:05]

⬇️ One-time download: 269 MB (Best model 238 MB + 31 MB audio engine, shared with the video tools) — only the first time: it stays saved in your browser, so next time it starts right away. (Translating or switching model needs its own file; a browser can clear this cache if storage runs very low.) Processing takes about 25-50 min per 10 minutes of audio on a typical laptop.

What exactly is downloaded — and is it safe?

• The speech model is OpenAI's Whisper, open source, converted to run in browsers. The audio engine is FFmpeg, the open-source tool behind most video software.
• They come from Hugging Face and unpkg — public repositories used by researchers and developers worldwide, not from us.
• They are not programs. Nothing is installed, no permission is asked, and your browser keeps them in its own cache exactly like it keeps a website's images.
• They can't read your files or touch anything outside this page. Remove them any time by clearing this site's data in your browser.
• Your audio never goes the other way: this site has no server receiving files.

Drop your video or audio here or click to choose

transcribed on your device by OpenAI's Whisper — your recording is not uploaded

ℹ️ Use a recording on your device that you own or have permission to process. This tool cannot fetch YouTube or social video links. Start with a short clip. Larger models can improve accuracy but require more memory and download data. Processing time varies by device, model and recording length. Always review the result.

Thai has five tones, 44 consonants and no spaces between words, and all three make it one of the harder languages for automatic transcription. An adequate model produces Thai with the wrong consonant for a homophone or a phrase break in an odd place. This page therefore opens with the Best model already selected, the largest of the three: a bigger one-time download and more processing time, in exchange for text accurate enough to proofread rather than retype.

Thai is also preset as the language, so a recording that starts with music or silence is not mistaken for Lao or Khmer, and the output follows Thai writing conventions: continuous characters within a phrase, spaces between phrases and sentences. Lectures, interviews, news clips and recorded calls in Central Thai are the typical material. OpenAI's Whisper runs inside your browser in Private mode; the engine and model are downloaded on first use and cached when possible, and the recording stays on your device. Copy the text or download a TXT, and use the subtitle exports for video.

The size of Best is the honest trade-off. On a phone or a laptop with little memory it can be slow or fail to load, in which case Accurate is the fallback. Strong Isan, northern or southern speech and fast chatter with overlapping voices need more editing than a clear lecture.

More sizes & options

Frequently asked questions

Why are there no spaces between words?: Because written Thai does not use them; spaces separate phrases. The output follows the normal convention, so it reads correctly to Thai readers.
Why Best by default?: Because the smaller models make many more mistakes in Thai. Best is slower but produces text that can be edited rather than retyped.
Does it handle Isan or southern speech?: Central Thai is most accurate. Strong regional speech loses accuracy, as dialects do in every language.
Will the Best model run on my phone?: Sometimes. Best needs more memory and time than the other models, so an older phone or a laptop with little RAM may struggle. If it stalls, switch to Accurate, which still handles clear Thai speech reasonably.
Can I save the Thai transcript as a file?: Yes. Download it as a TXT file in Thai script, or copy the text straight into a document or messaging app. For video, the subtitle exports include timestamps alongside the Thai text.

Guides

Related tools

🔒 Private mode (the default): your recording never leaves your device. Instant mode is optional, you switch it on yourself, and it sends the audio to the browser's speech service.