Scenario
In-car
In-car voice interaction, announcements and translation, with or without a network.
Audio
Speech recognition · speech synthesis · enhancement
Streaming ASR
24/7 real-time streaming transcription
Text appears as people speak; hours on end with flat speed and memory
- Fast response
- Unlimited length
- Chinese & English
Scenarios
Meetings Media & live Retail & service In-car Robotics
View demo
Streaming TTS
Multilingual, multi-voice real-time TTS
Starts speaking as text arrives; 10 languages, 9 voices, any length as one continuous stream
- Fast first sound
- 10 languages
- 9 voices
Scenarios
Robotics In-car Retail & service Smart home Media & live Education
View demo
Voice cloning
Zero-shot voice cloning
Clone a voice from a 5 s recording, no training; it can speak other languages, dialects and emotions
- 5 s of audio
- Cross-lingual
- Dialects & emotion
Scenarios
Media & live Retail & service In-car Education Robotics
View demo
Multimodal
Image & video understanding · embodied AI