Qwen 3 TTS - Voice Design [1.7B]
/v1/runQwen 3 TTS Voice Design 1.7b by Alibaba - convert text to natural-sounding speech with AI. Supports multiple voices, languages, emotions, and speaking styles for content creation and accessibility.
Request body
Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.
Model identifier. Set to alibaba/qwen-3-tts/voice-design/1.7b.
Default: alibaba/qwen-3-tts/voice-design/1.7b
Optional prompt to guide the style of the generated speech.
The text to be converted to speech.
Top-p sampling parameter.
Range: 0 to 1
Default: 1
Top-k for sub-talker sampling.
Minimum: 0
Default: 50
Top-k sampling parameter.
Minimum: 0
Default: 50
Temperature for sub-talker sampling.
Range: 0 to 1
Default: 0.9
Top-p for sub-talker sampling.
Range: 0 to 1
Default: 1
The language of the voice to be designed.
Allowed values: Auto, English, Chinese, Spanish, French, German, Italian, Japanese, Korean, Portuguese, Russian
Default: Auto
Maximum number of new codec tokens to generate.
Range: 1 to 8192
Default: 200
Sampling temperature; higher => more random.
Range: 0 to 1
Default: 0.9
Sampling switch for the sub-talker.
Default: true
Penalty to reduce repeated tokens/codes.
Minimum: 0
Default: 1.05
Response Schema
The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.
Opaque AGRouter run identifier. Use it exactly as returned; no prefix is guaranteed.
Current public run status.
Allowed values: pending, running, completed, failed, timeout
Public AGRouter model name used for this run.
Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.
Present only for failed or timeout runs. Contains a public error type and sanitized message.
Stable public error category.
Sanitized error message safe to show to clients.
Usage details when available.
Model capabilities
Capabilities declared by the model registry.
Default: text-to-speech
Execution mode declared by the model registry.
Default: async