Convert Chinese audio to text
Mandarin recordings (meetings, lectures, interviews) transcribed to proper Chinese text.
Free: 60 min per 30 days, files up to 30 min / 50 MB · Paid plans: 10 to 100 hrs, files up to 2 GB. Big video? Upload just its audio track: same transcript, much faster upload.
Encrypted in transit · audio & video auto-delete in 30 days · never used to train AI
Optional settings
Set this for the most accurate result on quiet or mixed audio.
Get a second copy translated into another language (Pro).
Uncommon words the AI might misspell. List them so they come out right.
Last updated 21 July 2026
Trustample converts Mandarin Chinese audio and video into written Chinese text: Simplified characters with punctuation placed by sentence context, ready to edit and export. Upload a meeting, lecture or interview, set the spoken language to Chinese before uploading for the most reliable detection, and the transcript arrives in a synced editor where any line replays with one click.
Mandarin arrives with many accents: Beijing retroflex and erhua, southern speakers who merge sh and s, the distinct rhythms of Taiwanese and Malaysian Mandarin. Accented Mandarin transcribes well when the audio is clear, and clarity is the operative word: because Mandarin is tonal, recognition degrades with microphone distance faster than English does, so a phone on the table beats a laptop across the room by a wider margin than usual.
Cross-border teams use the Pro translation to bridge languages: one upload of a Mandarin call yields both the Chinese transcript and an English version for colleagues, each checkable against the other. That is the workflow described in how to translate audio to text, applied to Chinese.
The output is real written Chinese (characters, not pinyin), which matters in a language whose speech doesn't pause where Western punctuation goes. The free plan asks for no card: the hour it includes each month absorbs a lecture or a long run of WeChat voice messages, in files up to 30 minutes with TXT export, so you can judge accuracy on your own Mandarin audio before paying anything.
How it works
- 1Set 'Spoken language' to Chinese under the upload box.
- 2Upload the recording; audio and video both work.
- 3Edit inline, export, and translate to English on Pro if needed.
Frequently Asked Questions (FAQs)
Simplified or Traditional characters?
Output is Simplified Chinese, the most widely used written form. Traditional-script output isn't offered today; converting Simplified→Traditional with an external tool is a workable bridge.
Does it handle Cantonese?
Mandarin is the supported Chinese variant. Cantonese speech transcribes unreliably, and we'd rather tell you that than let you waste minutes finding out.
How are English words inside Mandarin speech handled?
Common English tech terms and brand names inside Mandarin sentences usually survive intact, the way tech-industry Mandarin actually mixes them. A bilingual meeting that swings whole sentences between Mandarin and English is the harder case; transcribe it under whichever language holds the floor longest.
Can I get English subtitles from a Mandarin video?
Yes on Pro: transcribe Mandarin, export the Chinese SRT, and use the stored English translation to build an English caption track.
Does it work for Taiwanese or Singaporean Mandarin?
Yes, as accents of Mandarin: Guoyu spoken in Taiwan and Huayu spoken in Singapore both transcribe under the Chinese setting on clear audio. Two caveats: output remains Simplified characters even for Taiwanese speakers (convert externally if you need Traditional), and stretches of Hokkien, Cantonese or Singlish inside the recording won't transcribe reliably.
Can it output pinyin instead of characters?
No. The transcript is written Chinese in characters, which is what a transcript should be. If you need pinyin for language study, paste the text into any character-to-pinyin converter; that's transliteration, a separate job from transcription.
Is Mandarin transcription free to try?
Yes. The free hour each month is enough for a full lecture or several meetings' worth of testing, in files up to 30 minutes with TXT export and no credit card. Test it with your own recording; Mandarin accuracy is audio-dependent enough that your microphone matters more than any review.
An honest note: Tonal-language transcription is sensitive to audio quality: a decent microphone and minimal background noise matter more for Mandarin than for English. Cantonese isn't reliably supported.
Related pages
Japanese with kanji output
KoreanKorean audio with Hangul output
Meeting TranscriptionMeetings into minutes
Explore everything in Languages or browse all transcription tools.