Open 1.7B TTS model (Base, CustomVoice variants) for 10 languages with 3-second voice cloning.
Released
Jan 22, 2026
Context window
Not disclosed
Max output
Not disclosed
Parameters
1.7B
Input price
Not disclosed
Output price
Not disclosed
Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.
Pricing
No first-party API. This is an open-weights release you can run yourself.
Specifications
- Developer
- Alibaba
- Model type
- Audio gen
- Architecture
- Not disclosed
- Parameters
- 1.7B
- Input
- Text Audio
- Output
- Audio
- Knowledge cutoff
- Not disclosed
- License
- Apache License 2.0
- API access
- No first-party API