Live Chinese speech translation API

Translate Chinese speech to and from 60+ languages in real time. Low-latency streaming, 3,600 language pairs, and accurate translation for voice agents, live captioning, and multilingual apps.

Production-ready Chinese speech translation API

Real conversations in Chinese include accents, regional dialects, code switching, and domain-specific vocabulary. Soniox is built to handle that variation in a single model, so live translation stays usable across regions and registers.

Soniox preserves formatting in the translated transcript, including names, numbers, addresses, IDs, and domain-specific terms.

Chinese belongs to the Sino-Tibetan > Sinitic family. Soniox translates between Chinese and any of 60+ supported targets and 3,600 language pairs in total.

A breakthrough in real-time Chinese translation

check

Translate Chinese before the sentence ends

Meaning lands as it's spoken, not after the caption catches up.

check

Chinese paired with 60+ languages

Both source and target. 3,600 pairs total, not English-centric.

check

High quality Chinese output

Same model across every language, including historically underserved ones.

check

Native-speaker Chinese STT accuracy

Accurate translation starts with accurate recognition across accents, multilingual speech, and language switching.

check

Chinese names, numbers, and domain terms

Preserved in both transcript and translation, including phone numbers, emails, and IDs.

config.json
{
  "model": "stt-rt-v4",
  "translation": {
    "type": "one_way",
    "target_language": "zh"
  }
}

Transcription + translation through a single stream

Chinese translation is built on top of Soniox Speech-to-Text API. Every spoken word is transcribed, and translation streams mid-sentence and both arrive together in a single labeled token stream.

Turn it on by adding a translation block to your request. Translation runs on the same WebSocket and the same model. Translated tokens come back interleaved with transcripts, with no extra round trip.

Live Chinese translation: written and spoken

Chinese speech-to-text translation

micLive Chinese speecharrow_right_altsubjectTranscript + translation

Translate live Chinese into written text with the Soniox STT API. Enable real-time translation with a config change. Soniox streams the Chinese transcript and translated text as speech happens.

Use it for Chinese captions, subtitles, meeting translation, agent assist, accessibility tools, and multilingual transcription.

Chinese speech-to-speech translation

micLive Chinese speecharrow_right_altvolume_upTranslated speech

Build full spoken Chinese translation by combining Soniox STT and Soniox TTS. Soniox recognizes Chinese, translates it in real time, and speaks the output in the target language with low latency.

Use it for live Chinese interpreters, bilingual voice agents, travel assistants, customer support, and real-time multilingual communication.

Live Chinese translation for captions, conversations and more

Stream live Chinese translation in two modes: one-way translates all speech into a single target language, two-way keeps a bilingual conversation flowing between Chinese and another language.

voice_selection
Chinese speaker says: 群里那个milk tea的deal快没了,deadline是12:30,你要不要一起拼单?
translate
Speech is translated into English (or any of 60+ target languages) in real time.

One-way translation

Translate live speech to or from Chinese into a single target language. Everyone in the conversation sees the same translated stream.

Ideal for live captions, multilingual meetings, broadcasts, lectures, customer calls, and products where many speakers need to be understood in one language.

voice_selection
Chinese speaker talks in Chinese.
hearing
English speaker hears English.
voice_selection
English speaker replies in English.
hearing
Chinese speaker hears Chinese.

Two-way translation

Translate between Chinese and another language for live bilingual conversation. Each side speaks naturally and hears the other in their own language.

Soniox supports real-time two-way translation between any two of 60+ supported languages.

Built on the Soniox speech AI platform

Chinese translation is powered by the same infrastructure behind Soniox STT and TTS.

speech_to_text

Speech-to-Text

Native-speaker accuracy across 60+ languages, with support for multilingual speech, alphanumerics, speaker diarization, context.

translate

Translation

Real-time streaming translation across 3,600 language pairs, built for high quality and low delay across all supported languages.

text_to_speech

Text-to-speech

High-fidelity speech generation in 60+ languages, built for names, alphanumerics, language switching, and ultra-low-latency streaming.

Together, they create a complete real-time low-latency speech AI platform.

quiz
About Chinese

Chinese has roughly 1,100,000,000 speakers across China, Taiwan, and Singapore.

Chinese characters are one of the oldest continuously used writing systems, with over 3,000 years of history.

Chinese is a tonal language — Mandarin has four tones, and the same syllable can have different meanings depending on tone.

Frequently asked questions

Does Soniox translate Chinese in real time?arrow_downward
Yes. Soniox streams Chinese translation while speech is still happening, so users see or hear meaning immediately instead of waiting for the sentence to end.
What language pairs are supported for Chinese?arrow_downward
Soniox supports translation between Chinese and any of 60+ supported languages — 3,600 language pairs in total. Both Chinese as the source and Chinese as the target are supported.
How does two-way Chinese translation work?arrow_downward
Two-way translation lets both sides of a conversation speak in their own language and hear the other side in theirs. A Chinese speaker can talk in Chinese while the other party hears their own language in real time, and vice versa.
Does Soniox handle dialects and accents in Chinese?arrow_downward
Yes. Soniox handles Chinese dialects like Mandarin, Cantonese, and Wu in a single model, along with accents and language switching, so live translation stays accurate across regions and registers.
Can Soniox translate names, numbers, and domain terms in Chinese?arrow_downward
Yes. Soniox preserves the details that matter — names, phone numbers, emails, IDs, addresses, verification codes, and domain-specific terminology — in both the Chinese transcript and the translated output.
Which other providers support live Chinese translation?arrow_downward
Based on their public docs, OpenAI, Google, Azure, and Speechmatics list Chinese as a supported source language for real-time translation. Soniox is the only one of them that also supports two-way live translation across 60+ languages.
How fast is Chinese translation?arrow_downward
Soniox streams translated text as Chinese is being spoken, with ultra-low latency. Translation arrives before the sentence ends, rather than after long caption delays.
What can I build with Chinese translation?arrow_downward
Common use cases include multilingual voice agents, live interpreters, multilingual meetings, customer support and contact centers, real-time translated captions and subtitles, and accessibility and communication tools — all with Chinese as a source or target.

Ready to get started?

Create an account instantly, or contact us to design a custom package for your business.

Build with API arrow_right_alt

Documentation

Get up and running in minutes and spend your time building the product, not wrestling with the API.

Explore docs

See what you’ll pay

Pay only for what you use with our flexible pricing. Built to scale with you.

Pricing details