Text to speech

Call Ali qwen3-tts-instruct-flash through the unified /v1/audio/speech endpoint.

Response contract:

• non-streaming returns the official Ali JSON response;
• streaming returns text/event-stream and forwards Ali SSE payloads.

POST /v1/audio/speech

cURL

basic

curl --request POST \
  --url https://baze-api.powerbuyin.top/v1/audio/speech \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen3-tts-instruct-flash",
  "input": "Introduce this product with a slightly faster speaking rate.",
  "voice": "Cherry",
  "instructions": "Speak faster with a brighter tone.",
  "optimize_instructions": false,
  "language_type": "English"
}
'

200

{
  "status_code": 123,
  "request_id": "<string>",
  "code": "<string>",
  "message": "<string>",
  "output": {
    "text": null,
    "finish_reason": "<string>",
    "choices": null,
    "audio": {
      "data": "<string>",
      "url": "<string>",
      "id": "<string>",
      "expires_at": 123
    }
  },
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123,
    "total_tokens": 123,
    "characters": 123
  }
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

X-DashScope-SSE · enum<string>

Official Ali HTTP streaming switch. Send enable to receive text/event-stream.

Available options: enable

Body

application/json

model · enum<string> · required

Available options: qwen3-tts-instruct-flash

input · string · required

Input text to synthesize.

voice · enum<string> · required

System voice name. Only the enum values listed here are currently supported on this channel.

Available options: Cherry, Serena, Ethan, Chelsie, Momo, Vivian, Moon, Maia, Kai, Nofish, Bella, Eldric Sage, Mia, Mochi, Bellona, Vincent, Bunny, Neil, Elias, Arthur, Nini, Seren, Pip, Stella

instructions · string

Style-control instruction.

optimize_instructions · boolean

Whether to optimize instructions. An explicit false is preserved and forwarded.

language_type · enum<string>

Language type.

Available options: Auto, Chinese, English, German, Italian, Portuguese, Spanish, Japanese, Korean, French, Russian

Response

200

application/json

Successful call. Non-streaming returns the official Ali JSON response; streaming returns Ali SSE payloads.

status_code · integer

HTTP status code.

request_id · string

Ali request ID.

code · string

Error code. Usually empty on success.

message · string

Error message. Usually empty on success.

output · object

Show child attributes

usage · object

Show child attributes