Qwen 3 TTS - Text to Speech [0.6B]

POST/v1/run

Qwen 3 Tts 0.6b is Alibaba's text-to-speech AI model. Generate human-like voiceovers with expressive intonation, multilingual support, and customizable voice characteristics.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to alibaba/qwen-3-tts/0.6b.

Default: alibaba/qwen-3-tts/0.6b

stringpromptrequired

Optional prompt to guide the style of the generated speech. This prompt will be ignored if a speaker embedding is provided.

Optional<string>text

The text to be converted to speech.

Optional<number>top_p

Top-p sampling parameter.

Range: 0 to 1

Default: 1

Optional<number>subtalker_top_p

Top-p for sub-talker sampling.

Range: 0 to 1

Default: 1

Optional<string>voice

The voice to be used for speech synthesis, will be ignored if a speaker embedding is provided. Check out the **[documentation](https://github.com/QwenLM/Qwen3-TTS/tree/main?tab=readme-ov-file#custom-voice-generate)** for each voice's details and which language they primarily support.

Allowed values: Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, Aiden, Ono_Anna, Sohee

Optional<number>repetition_penalty

Penalty to reduce repeated tokens/codes.

Range: 0 to ∞

Default: 1.05

Optional<integer>subtalker_top_k

Top-k for sub-talker sampling.

Range: 0 to ∞

Default: 50

Optional<integer>top_k

Top-k sampling parameter.

Range: 0 to ∞

Default: 50

Optional<string>reference_text

Optional reference text that was used when creating the speaker embedding. Providing this can improve synthesis quality when using a cloned voice.

Optional<number>temperature

Sampling temperature; higher => more random.

Range: 0 to 1

Default: 0.9

Optional<integer>max_new_tokens

Maximum number of new codec tokens to generate.

Range: 1 to 8192

Default: 200

Optional<string>language

The language of the voice.

Allowed values: Auto, English, Chinese, Spanish, French, German, Italian, Japanese, Korean, Portuguese, Russian

Default: Auto

Optional<boolean>subtalker_dosample

Sampling switch for the sub-talker.

Default: true

Optional<number>subtalker_temperature

Temperature for sub-talker sampling.

Range: 0 to 1

Default: 0.9

Optional<string>speaker_voice_embedding_file_url

URL to a speaker embedding file in safetensors format, from `fal-ai/qwen-3-tts/clone-voice/0.6b` endpoint. If provided, the TTS model will use the cloned voice for synthesis instead of the predefined voices.

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: text-to-speech

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/qwen-3-tts/0.6b",
  "prompt": "Very happy.",
  "text": "I feel like I'm taking crazy pills! How can something be both a square and a circle at the same time? It defies all logic!",
  "voice": "Vivian"
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/run_abc123 \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "run_abc123",
  "model": "alibaba/qwen-3-tts/0.6b",
  "status": "running",
  "outputs": []
}