Simplified or traditional characters?

Simplified by default. If you need traditional, convert the output with any standard converter — the wording stays identical.

Partially, with noticeably lower accuracy than Mandarin. Use the Best model and expect to correct the result.

Is punctuation added?

Yes — full-width Chinese punctuation is inserted automatically, which is what makes the transcript readable.

Does it transcribe Taiwanese Mandarin?

Yes. The speech is handled as Mandarin and transcribed well; the output is in simplified characters by default, so convert to traditional afterwards if that is what you need. The text itself does not change.

Can I get pinyin instead of characters?

No. The transcript is in Chinese characters only. If you need pinyin for study, paste the result into a separate converter; most online pinyin tools accept pasted text and add tone marks.

Transcribe Chinese Audio to Text — Free, No Upload

Convert Mandarin audio or video into Chinese characters in your browser. 100% free, no per-minute limit, private — nothing is uploaded.

Model

Spoken

Output

Timestamps [0:05]

⬇️ One-time download: 104 MB (Accurate model 73 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 4-8 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.

Written Chinese has no spaces, so a transcription tool has to do more than hear syllables: it has to decide where words begin and end, choose between homophones, and place punctuation, or the result is an unreadable stream of characters. Whisper does that from context, which is why a Mandarin lecture, a recorded interview or a podcast comes out as readable prose with 。and ，in sensible places. This page opens with Chinese preselected, so a short clip is not misdetected as Japanese or Korean.

The model runs in your browser: the recording is not uploaded and there is no per-minute charge. Copy the text, download TXT, or export subtitles in SRT or VTT. Chinese is harder for the smaller models than English, so choose Accurate or Best for anything beyond a clear studio voice; the larger model is a bigger one-time download but noticeably better at tones and homophones.

The limits to know. Output is in simplified characters; traditional can be produced by converting afterwards with any standard tool, and the wording is identical. Mandarin is well supported; Cantonese is a different spoken language and comes out considerably weaker. Names, numbers and technical terms deserve a check, as does anything spoken in English within the Chinese, since the model follows the selected language.

More sizes & options

Frequently asked questions

Simplified or traditional characters?: Simplified by default. If you need traditional, convert the output with any standard converter — the wording stays identical.
Does Cantonese work?: Partially, with noticeably lower accuracy than Mandarin. Use the Best model and expect to correct the result.
Is punctuation added?: Yes — full-width Chinese punctuation is inserted automatically, which is what makes the transcript readable.
Does it transcribe Taiwanese Mandarin?: Yes. The speech is handled as Mandarin and transcribed well; the output is in simplified characters by default, so convert to traditional afterwards if that is what you need. The text itself does not change.
Can I get pinyin instead of characters?: No. The transcript is in Chinese characters only. If you need pinyin for study, paste the result into a separate converter; most online pinyin tools accept pasted text and add tone marks.

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.