Transcribe Chinese Audio
Mandarin is one of the strongest languages in Whisper-class models. Upload Chinese meetings, courses or interviews and get accurate transcripts with proper punctuation — in simplified or traditional characters.
- AI transcription
- 98 Languages
- Encrypted; we never train AI on your files
Start with your recording
Drop an audio or video file here, or click to choose.
What you get: a real transcript
Unedited output from a 64-second interview with two speakers (synthetic voices), transcribed with speaker detection on. Only the first lines are shown.
SPEAKER_00 (0:00) Welcome back to Small Shop Stories. SPEAKER_00 (0:02) Today I'm talking to Maya, who runs a tiny bakery on the SPEAKER_00 (0:05) corner of Mill Street. SPEAKER_01 (0:07) Thanks for having me. SPEAKER_01 (0:08) It's really small, just two ovens and a counter. SPEAKER_00 (0:12) So how does a normal day start for you?
1 00:00:00,000 --> 00:00:01,680 [SPEAKER_00] Welcome back to Small Shop Stories. 2 00:00:02,160 --> 00:00:05,320 [SPEAKER_00] Today I'm talking to Maya, who runs a tiny bakery on the 3 00:00:05,320 --> 00:00:06,320 [SPEAKER_00] corner of Mill Street.
Checked against the script, 4 of 189 words differed — a 2.1% word error rate, counting "80" written for "eighty" as an error — and all 14 speaker turns were labelled correctly. This was clean speech; noisy recordings and people talking over each other score lower. See the full transcript and how it was scored
How it works
- 1
Upload
Drop in an audio or video file, or paste a link. All common formats are accepted.
- 2
Transcribe
AI transcribes with timestamps and optional speaker labels, usually in minutes.
- 3
Export
Edit segments online, then export TXT, SRT, VTT, TSV, CSV, JSON, PDF or DOCX.
Why ScribeToAny
- Mandarin & Accents: Strongest on standard Putonghua; Taiwanese Mandarin and regional accents work, heavy accents less reliably.
- Chinese Characters: Usually written in simplified characters; there's no simplified/traditional switch yet, so convert with a tool like OpenCC if you need traditional.
- Mixed Chinese & English: Code-switched speech is transcribed in place, with English terms in Latin letters; uncommon brand names may need a fix.
- Chinese-Sized Subtitles: Cues are capped at about 32 characters and broken at 。，、 — sized for Chinese reading rather than English line lengths.
Frequently asked questions
Does it handle Chinese-English code-switching?
Yes — mixed Mandarin/English speech, common in tech and business settings, is transcribed in place.
Simplified or traditional characters?
Transcripts are usually written in simplified characters, but there's no simplified/traditional switch yet, and a clip can occasionally come back in traditional. If you need a specific script, convert the finished text with a converter such as OpenCC before publishing.
Can it subtitle Chinese videos?
Yes, export SRT/VTT with speech-aligned timing for any Chinese video.
Which language option should I pick for Mandarin?
Choose 简体中文 under Audio language when you know the audio is Mandarin; Taiwanese Mandarin uses the same option. Auto-detect decides from roughly the first 30 seconds, so a clip that opens with music or English can be read as another language — choosing the language skips that guess.
How are Chinese subtitles split into lines?
Chinese cues are capped at about 32 characters — roughly two lines of 16 — instead of the 84 used for English, and breaks prefer 。，、 so a caption doesn't stop mid-phrase. Whisper-class models usually add Chinese punctuation; where they don't, cues are cut by length instead. Any cue that still reads awkwardly can be split in the editor.