What is Cantonese speech to text and how does it work?

Speech to text (also called automatic speech recognition, or ASR) converts spoken Cantonese audio into written text. Deepgram processes the audio signal, detects speech in real time, and returns structured transcript data through an API. Developers use it for applications like voice agents, call analytics, captioning, and searchable media.

Does Deepgram support Cantonese speech to text?

Yes. Deepgram supports automatic speech recognition (ASR) for Cantonese audio. You can transcribe real-time or prerecorded audio by setting `language=zh-HK` in your API request.

Which Deepgram models support Cantonese speech to text?

Deepgram supports Cantonese in the Nova model family. Model availability may vary by language, so check the Models & Languages page for the latest support details.

Can Deepgram transcribe Cantonese in real time?

Yes. Deepgram provides low-latency streaming transcription for Cantonese, suitable for live voice agents, call analytics, captioning, and other real-time applications.

Does Deepgram support automatic language detection for Cantonese?

Deepgram offers automatic language detection for many languages. You can enable it with `detect_language=true`. See the Language Detection documentation for the full list of supported languages.

Can Deepgram handle audio with multiple languages or code-switching?

Yes. Deepgram supports multilingual transcription and code-switching when using Nova's multilingual models. Set `language=multi` to enable it. See the Models & Languages page for supported languages.

What features are supported for Cantonese transcripts?

Deepgram supports timestamps, punctuation, diarization, numeral formatting, filler-word detection, redaction, and more — all through the API.

How accurate is Deepgram for Cantonese speech to text?

Accuracy depends on model choice, audio quality, and domain. Nova models deliver state-of-the-art accuracy, and you can improve results further using Keyterm Prompting or Custom Models.

How do I get started with Deepgram's Cantonese Speech-to-Text API?

Sign up for a free Deepgram account to access your API key. You can test Cantonese transcription instantly in the Playground , or call the API directly by sending audio to `/v1/listen` with `language=zh-HK`. Starter apps and code examples are available on GitHub.

Cantonese Speech to Text API | Fast & Accurate Transcription

Cantonese Speech to Text

Convert Cantonese speech to text with high accuracy, low latency, and enterprise-grade scalability. Deepgram delivers real-time and batch transcription through a developer-first speech-to-text API.

Sign Up Free Contact Sales

OR

Your transcriptions will show here.

Trusted by the world's top Enterprises and Startups

Fast and accurate Cantonese speech recognition for real-world audio

Get real-time Cantonese speech-to-text in under 300 ms while maintaining high accuracy in noisy, accented, or overlapping conversations.

Cantonese Language Overview

Speakers: 85-86 million worldwide

Regions: China (Guangdong and Guangxi), Hong Kong, Macau, Malaysia, United States, Vietnam, Singapore, Australia, United Kingdom, Canada

Dialects: Guangzhou Cantonese (standard), Hong Kong Cantonese, Macau Cantonese, Taishanese (Toisanese)

Writing system: Traditional Chinese characters with Cantonese-specific colloquial characters

Language family: Sino-Tibetan, Yue branch of Chinese languages

Cantonese is widely used across Hong Kong, southern China, and global diaspora communities, making it a key language for call center analytics, customer support AI, media captioning, healthcare transcription, multilingual voice agents, financial services, and legal documentation.