Skip to main content
Real-time speech recognition (Paraformer)

Server-sent events for real-time speech recognition (Paraformer)

Reference for the server-sent events that the Paraformer real-time speech recognition service pushes to clients over WebSocket. This topic documents the data structure and field semantics of the four event types: task-started, result-generated, task-finished, and task-failed.

User guide: For model details and selection guidance, see Speech-to-text. Event interaction flow: For the event sequence diagram, see WebSocket API.

task-started

Description: The task has started successfully. The client can begin sending audio data.
headerobject

Properties

task_idstringClient-generated task ID (UUID format).eventstringEvent type. Always task-started.attributesobjectAdditional attributes. Typically empty.
payloadobjectAlways {}.
{
    "header": {
        "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
        "event": "task-started",
        "attributes": {}
    },
    "payload": {}
}

result-generated

Description: Recognition result. Includes intermediate results (sentence_end=false) and final results (sentence_end=true).
headerobject

Properties

task_idstringClient-generated task ID (UUID format).eventstringEvent type. Always result-generated.
payloadobject

Properties

outputobject

Properties

usageobjectWhen payload.output.sentence.sentence_end is false (the current sentence has not ended), usage is null.When payload.output.sentence.sentence_end is true (the current sentence has ended), usage.duration indicates the billable duration of the current task.

Properties

durationintegerBillable task duration, in seconds.

Properties

sentenceobject

Properties

begin_timeintegerSentence start time, in milliseconds.end_timeintegerSentence end time, in milliseconds.textstringRecognized text.heartbeatbooleanIf true, you can skip this result (heartbeat packet).sentence_endbooleanWhether the sentence has ended (true=final result, false=intermediate result).emo_tagstring
  • Only paraformer-realtime-8k-v2 supports this feature.
  • This feature requires semantic segmentation to be disabled. Set semantic_punctuation_enabled to false in the run-task event.
  • The emotion recognition result is returned only when payload.output.sentence.sentence_end is true.
Sentiment of the current sentence:
  • positive: Positive sentiment, such as happy or satisfied.
  • negative: Negative sentiment, such as angry or dejected.
  • neutral: No distinct sentiment.
emo_confidencefloat
  • Only paraformer-realtime-8k-v2 supports this feature.
  • This feature requires semantic segmentation to be disabled. Set semantic_punctuation_enabled to false in the run-task event.
  • The emotion recognition result is returned only when payload.output.sentence.sentence_end is true.
Emotion confidence score in the range [0.0, 1.0]. A higher value indicates greater confidence.wordsarray[object]Word-level timestamp information.

Properties

begin_timeintegerWord start time, in milliseconds.end_timeintegerWord end time, in milliseconds.textstringRecognized text.punctuationstringPunctuation mark.
{
  "header": {
    "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
    "event": "result-generated",
    "attributes": {}
  },
  "payload": {
    "output": {
      "sentence": {
        "begin_time": 170,
        "end_time": null,
        "text": "Okay, I got it.",
        "heartbeat": false,
        "sentence_end": true,
        "words": [
          {
            "begin_time": 170,
            "end_time": 295,
            "text": "Okay",
            "punctuation": ","
          },
          {
            "begin_time": 295,
            "end_time": 503,
            "text": "I",
            "punctuation": ""
          },
          {
            "begin_time": 503,
            "end_time": 711,
            "text": "got",
            "punctuation": ""
          },
          {
            "begin_time": 711,
            "end_time": 920,
            "text": "it",
            "punctuation": ""
          }
        ]
      }
    },
    "usage": {
      "duration": 3
    }
  }
}

task-finished

Description: The task ended normally. You can close the connection or reuse it.
headerobject

Properties

task_idstringClient-generated task ID (UUID format).eventstringEvent type. Always task-finished.attributesobjectAdditional attributes. Typically empty.
payloadobjectThe contents can be ignored. Typically {}.
{
    "header": {
        "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
        "event": "task-finished",
        "attributes": {}
    },
    "payload": {
        "output": {},
        "usage": null
    }
}

task-failed

Description: The task failed. The connection is closed and cannot be reused.
headerobject

Properties

task_idstringClient-generated task ID (UUID format).eventstringEvent type. Always task-failed.error_codestringDescription of the error type.error_messagestringSpecific cause of the error.attributesobjectAdditional attributes. Typically empty.
payloadobjectAlways {}.
{
    "header": {
        "task_id": "2bf83b9a-baeb-4fda-8d9a-xxxxxxxxxxxx",
        "event": "task-failed",
        "error_code": "CLIENT_ERROR",
        "error_message": "request timeout after 23 seconds.",
        "attributes": {}
    },
    "payload": {}
}
Text Generation
Image Generation
  • FAQ
Video Generation
Audio
Realtime API
Text Embedding
Model Production