Retail & service
Shopping assistants, multilingual service and marketing visuals, even offline.
Audio
Speech recognition · speech synthesis · enhancement
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
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
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
LLM
Chat · agents · function calling
Translate between languages
Translate directly between common languages, with consistent terms and the formatting kept, no network needed
- Consistent terms
- Formatting kept
- Works offline
Multimodal
Image & video understanding · embodied AI
Read once, decide instantly
Turn text or images into structured decisions; process several questions together and compare candidate answers with option probabilities
- Text & images
- Multiple questions
- Structured answers
Long video understanding
With the same on-device budget it takes in 8x as much video as usual approaches, so it follows a whole sequence of actions, not a single moment
- Whole sequences
- 8x the video, same budget
- Q&A and summaries
Generative AI
Text-to-image · image editing · video generation