Speech-to-speech translation
Send live audio over a secure WebSocket and receive translated speech in near real time. Zoom's Interpreter service provides a clear translation with demonstrated accuracy.
Zoom AI Services: Interpreter API (Preview)
Break the language
barrier in real time
Stream speech in one language and hear it spoken back in another, all through a single API connection. Interpreter API delivers real-time speech-to-speech translation so participants can follow the conversation in their preferred language. Choose from 9 supported languages and a selection of natural-sounding AI voices.
Capabilities
One voice, multiple languages
9 languages
Translate between any of these 9 languages: English, Arabic, Chinese (Simplified), French, German, Italian, Japanese, Portuguese, Spanish.
AI voice selection
Pick from a male and a female voice for each of the supported languages.
Transcript and translated text
Receive a bilingual transcript alongside the audio stream to support accessibility, compliance, and post-session review.
Performance
Translation quality you can measure
Independent benchmarking shows Zoom Interpreter API delivering industry-leading speech translation quality, scoring 74.21 out of 100. This result highlights Zoom's edge in real-time, accurate cross-language communication, giving developers a translation engine they can trust for multi-language conversations.
One foundation
Make every conversation multilingual
Start with real-time speech translation, then adapt the experience for the people and systems that need it.
Contact center support
Enable agents to speak with customers in their preferred language — no human interpreter required. Both sides hear a natural-sounding translated voice while the original audio remains available for quality review.
Realtime translation applications
Create realtime speech to speech translation applications for travelers, language learners, etc.
Field service & frontline
Connect technicians, healthcare workers, and field staff with clients who speak a different language. Real-time spoken translation helps maintain efficient and accurate communication when time matters.
See demo
Speak one language. Hear another.
Watch the Interpreter API in action — see how speech in one language is instantly translated into natural-sounding speech in another. The demo video walks through the full pipeline, highlighting the original transcript, translated text, and translated audio playback side by side, along with source and target language selection, AI voice options, and end-to-end latency.
Try the playgroundPricing
Simple, transparent pricing
Apply prepaid credits to your use of Interpreter API with transparent rates.
Interpreter API
$2/hour
Speech-to-Speech Interpreter API converts live speech in one language into natural-sounding speech in another language, enabling real-time multilingual voice communication.
Usage is measured based on the total duration of audio processed in minutes during a given billing period.
Get startedDeveloper resources
Everything you need to integrate, build, and ship with Zoom Interpreter API.
