Skip to main content

Sambert server-sent events

User guide: For model introduction and selection recommendations, see Speech synthesis.
Alibaba Cloud Model Studio has released a workspace-specific domain for the China (Beijing) region: https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com. The new dedicated domain delivers superior performance and higher stability for inference requests. We recommend migrating from https://dashscope.aliyuncs.com to the new domain.{WorkspaceId} is your workspace ID, which can be found on the Workspace Details page in the Alibaba Cloud Model Studio console. The existing domain remains fully functional.

task-started

When the client sends the run-task command, the server returns a task-started event to indicate the task has started.
header.task_idstringThe task ID generated by the client.header.eventstringThe event type. Fixed value: task-started.payloadobjectEmpty object with no content.
{
  "header": {
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "event": "task-started",
    "attributes": {}
  },
  "payload": {}
}

result-generated

After the client sends text, the server streams result-generated events. Each event includes full timestamp data in output.sentence, with word-level and phoneme-level timestamps when the corresponding parameters are enabled.
header.task_idstringThe task ID generated by the client.header.eventstringThe event type. Fixed value: result-generated.payload.outputobjectThe synthesized audio output.

Properties

sentence.begin_timeintegerThe begin timestamp of the sentence. Unit: milliseconds.sentence.end_timeintegerThe end timestamp of the sentence. Unit: milliseconds.sentence.wordsarrayWord-level timestamps for each word in the sentence.

Element properties of words

textstringThe text content of the word.begin_timeintegerThe begin timestamp of the word in the audio. Unit: milliseconds.end_timeintegerThe end timestamp of the word in the audio. Unit: milliseconds.phonemesarray(requires phoneme_timestamp_enabled)Phoneme-level timestamps for each phoneme in the word.

Element properties of phonemes

textstringThe phoneme text.toneintegerThe tone value.begin_timeintegerThe begin timestamp of the phoneme. Unit: milliseconds.end_timeintegerThe end timestamp of the phoneme. Unit: milliseconds.
payload.usageobjectBilling usage for the current event.

Properties

charactersintegerThe cumulative billed character count up to the current event.
{
  "header": {
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "event": "result-generated",
    "attributes": {}
  },
  "payload": {
    "output": {
      "sentence": {
        "begin_time": 0,
        "end_time": 1162,
        "words": [
          {
            "text": "Bed",
            "begin_time": 0,
            "end_time": 263,
            "phonemes": [
              {
                "begin_time": 0,
                "end_time": 119,
                "text": "ch_c",
                "tone": 2
              }
            ]
          }
        ]
      }
    },
    "usage": {
      "characters": 6
    }
  }
}

task-finished

When the task is complete, the server returns a task-finished event. The client can then close the WebSocket connection or reuse the connection for a new task.
header.task_idstringThe task ID generated by the client.header.eventstringThe event type. Fixed value: task-finished.payload.usage.charactersintegerThe cumulative billed character count up to the current event.
{
  "header": {
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "event": "task-finished",
    "attributes": {
      "request_uuid": "0a9dba9e-d3a6-45a4-be6d-xxxxxxxxxxxx"
    }
  },
  "payload": {
    "usage": {
      "characters": 13
    }
  }
}

task-failed

When a task fails, the server returns a task-failed event. Close the WebSocket connection and handle the error.
header.task_idstringThe task ID generated by the client.header.eventstringThe event type. Fixed value: task-failed.header.error_codestringThe error code.header.error_messagestringThe detailed error message.
{
  "header": {
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "event": "task-failed",
    "error_code": "InvalidParameter",
    "error_message": "[tts:]Engine return error code: 418",
    "attributes": {}
  },
  "payload": {}
}
API Usage
Text Generation
Image Generation
Video Generation
World models
3D Model Generation
Audio
Real-time Multimodal
Realtime API
Text Embedding
Translation models
Decision Model
More Models
Toolkit/Framework
TokenPlan
Model Production
File Management
Billing
Model Management
More