Standard & Paid Price
Standard Price
| Meter | Standard Price |
|---|---|
| Input price | $0.1800 / 10K characters |
Billing details
Description
Alibaba Qwen-Audio-3.0-TTS-Flash — speech synthesis on the Qwen-Audio 3.0 base tuned for realtime interaction, covering more minority languages and Chinese dialects than the previous generation. Free-style instruction following and fine-grained tags steer emotion, tone, character, rate, and volume; the model is more robust under noise and reverberation. The flash tier optimises for low-latency synthesis, for voice assistants, live dialogue, and support agents. Billed per character (1 token = 1 character). Reachable both as a request/response call and as a realtime WebSocket session.
Capabilities
- Tasks
- text-to-speech
API endpoints
POST /v1/audio/speech(audio-speech)GET /v1/realtime(realtime)