Speech Recognition (Streaming Output)

​

Endpoint

​

Request Headers

• Content-Type string required
  Must be application/json.
• Accept string required
  Must be text/event-stream.
• Authorization string required
  Authentication token in the format Bearer $STEPFUN_API_KEY.

​

Request Parameters

• audio object required
  Audio data and recognition configuration.

  Show child attributes

  • data string required
    Base64-encoded audio data.
  • input object required
    Recognition and audio format configuration.

    Show child attributes

    • transcription object
      Recognition configuration.

      Show child attributes

      • language string
        Recognition language, e.g. zh.
      • model string
        Model name. Supports stepaudio-2.5-asr.
      • enable_itn bool optional
        Whether to enable ITN (inverse text normalization). Default true.
    • format object
      Audio format.

      Show child attributes

      • type string
        Audio container format. Supports ogg, mp3, wav, pcm, m4a.
      • codec string
        Codec; when type=pcm, typically pcm_s16le.
      • rate int
        Sample rate; required for pcm, optional for other formats.
      • bits int
        Bit depth; required for pcm, optional for other formats.
      • channel int
        Channel count; required for pcm, optional for other formats.

​

Request Example

{
  "audio": {
    "data": "audioData",
    "input": {
      "transcription": {
        "language": "zh",
        "model": "stepaudio-2.5-asr",
        "enable_itn": true
      },
      "format": {
        "type": "pcm",
        "codec": "pcm_s16le",
        "rate": 16000,
        "bits": 16,
        "channel": 1
      }
    }
  }
}

• Audio data must be Base64-encoded.
• Supported audio formats: ogg, mp3, wav, pcm, m4a.
• When the audio format is pcm, rate, bits, and channel are required; for ogg, mp3, wav, and m4a they are optional.

​

Response

​

Delta event (transcript.text.delta)

{
  "type": "transcript.text.delta",
  "meta": {
    "session_id": "sse_1642694400123456789",
    "timestamp": 1642694400123
  },
  "delta": "recognized "
}

• type string
  Event type. Fixed as transcript.text.delta.
• meta.session_id string
  Session ID.
• meta.timestamp int64
  Server-side event Unix timestamp, in milliseconds.
• delta string
  Incremental transcription text.

​

Done event (transcript.text.done)

{
  "type": "transcript.text.done",
  "meta": {
    "session_id": "sse_1642694400123456789",
    "timestamp": 1642694400456
  },
  "text": "The complete recognized text",
  "usage": {
    "type": "tokens",
    "input_tokens": 1000,
    "input_token_details": {
      "text_tokens": 0,
      "audio_tokens": 1000
    },
    "output_tokens": 50,
    "total_tokens": 1050
  }
}

• type string
  Event type. Fixed as transcript.text.done.
• meta.session_id string
  Session ID.
• meta.timestamp int64
  Unix timestamp, in milliseconds.
• text string
  The complete transcription text.
• usage object
  Usage statistics.

​

Error event (error)

{
  "type": "error",
  "meta": {
    "session_id": "sse_1642694400123456789",
    "timestamp": 1642694400789
  },
  "message": "Error description"
}

• type string
  Event type. Fixed as error.
• meta.session_id string
  Session ID.
• meta.timestamp int64
  Unix timestamp, in milliseconds.
• message string
  Error description.