Free Cantonese Speech to Text Transcription
Free Cantonese Automatic Speech Recognition (ASR) using our advanced AI transcription tool, Scribe. ElevenLabs beats Google Gemini and OpenAI Whisper in testing, with word error rates of just 5.9% on the FLEURS benchmark and 8.0% on the Common Voice benchmark. Industry-leading transcriptions for Cantonese films, podcasts, business meetings, medical dictations and more.
Upload an audio/video file or start recording to generate a transcript
Experience the full Audio AI platform
Every word, perfectly captured
Scribe listens to every nuance, capturing each Cantonese word with unmatched precision. Delivering audio transcription in 99 languages—with character-level timestamps, speaker diarization, and audio-event tagging—it returns structured results for seamless integration
Cantonese Transcription Benchmark
| Model | FLEURS |
|---|---|
Scribe v1 | 5.9% WER |
Deepgram Nova 2 | 19.3% WER |
Gemini Flash 2 | 17.6% WER |
Whisper Large v3 | 13.2% WER |
Powerful Audio to Text features for your app
Transform your Cantonese audio into flawless text with Scribe, the world's most advanced ASR (automatic speech recognition) model with the simplest speech to text API integration
Industry-leading accuracy
Achieve precision like never before—Scribe delivers the industry's lowest word error rate for perfectly accurate Cantonese transcription
Smart speaker diarization
In any conversation, even the busiest ones, Scribe intuitively distinguishes and labels every speaker for clear, organized transcripts
Precise word-level timestamps
Capture the exact moment each word is spoken. Scribe's detailed timestamps enable seamless subtitle syncing and interactive audio experiences
Dynamic audio tagging
From laughter to footsteps, Scribe's transcription model tags every sound event, enriching your Cantonese transcripts with the full context of your audio
Global language support
Break language barriers with support for Cantonese and 98 other languages—Scribe unlocks AI transcription capabilities for languages previously out of reach
Language Overview
Cantonese Language Information
Speakers: 85 million Accents: Hong Kong (Standard), Guangzhou, Macau, Malaysian Cantonese Official language in: Hong Kong and Macau (as Chinese) Spoken in: Southern China (Guangdong, Guangxi), Hong Kong, Macau, and among Chinese diaspora communities A Chinese language known for its six to nine tones (depending on analysis). Preserves more features from Middle Chinese than Mandarin and has a rich tradition of distinctive written vernacular.
Developers
Integrate ElevenLabs Scribe
Seamlessly integrate the world's most accurate speech to text model for Cantonese, into your application. Get started with our developer-friendly examples that showcase features like diarization, character-level timestamps, and audio-event tagging for flawless transcriptions
AI Speech to Text transcription in 99 languages
Our AI speech to text transcription supports 99 languages, just select the language and upload your audio file.