Qwen Voice Clone (1.7B)
qwen-voice-cloneGenerate a reusable Qwen speaker embedding from a short reference clip (zero-shot voice cloning).
- Speech to text
Pricing
Includes our margin. Charged per request from your balance.
- Per minute
- $0.47
Details
- Provider
- Qwen
- Added
- Nov 5, 2026
Options
Parameters this model accepts.
- Features
- Zero-shot voice cloning, Outputs speaker embedding (.safetensors), Works with Qwen 3 TTS, Optional reference text improves quality
- Response formats
- json
- Input formats
- MP3, OGG, WAV, M4A, AAC
- Max file size
- 500 MB
- Max upload in the request
- 4 MB
- File URLs
- Supported