MOSI · ASR

MOSS Transcribe Diarize Pro

Speech transcription with speaker-aware segments for conversations and meetings.

moss-transcribe-diarize-pro

$0.005 / audio minuteTry in Console

Current model-specific price from our catalog. Requests require your project API key and sufficient balance. Availability is checked at execution time.

Input and capabilities

Upload a short audio or video file using multipart/form-data: at most 30 seconds and 20 MiB. Use WAV for the examples below. Container compatibility depends on the model.

transcription
diarization
segment timestamps
hotwords

Automatic language detection: supported.

API endpoint

POST https://api.speechinfra.com/v1/inference/moss-transcribe-diarize-pro

Authenticate with your Speechinfra project key. Read the quickstart and billing guide.

cURL

curl --fail-with-body "https://api.speechinfra.com/v1/inference/moss-transcribe-diarize-pro" \
  -H "Authorization: Bearer $SPEECH_API_KEY" \
  -F "file=@clip.wav" \
  --form-string "diarize=true" \
  --form-string "response_format=diarized_json"

Python

# pip install httpx
import os
import httpx

headers = {"Authorization": "Bearer " + os.environ["SPEECH_API_KEY"]}
with open("clip.wav", "rb") as audio:
    response = httpx.post(
        "https://api.speechinfra.com/v1/inference/moss-transcribe-diarize-pro",
        headers=headers, files={"file": ("clip.wav", audio, "audio/wav")},
        data={
    "diarize": "true",
    "response_format": "diarized_json"
}, timeout=90,
    )
response.raise_for_status()
print(response.json())

Node.js / fetch

// Node.js 22+, no SDK required.
import { readFile } from 'node:fs/promises';
const form = new FormData();
form.set('file', new Blob([await readFile('clip.wav')]), 'clip.wav');
for (const [key, value] of Object.entries({
  "diarize": "true",
  "response_format": "diarized_json"
})) form.set(key, value);
const response = await fetch("https://api.speechinfra.com/v1/inference/moss-transcribe-diarize-pro", {
  method: 'POST', body: form, signal: AbortSignal.timeout(90000),
  headers: { Authorization: 'Bearer ' + process.env.SPEECH_API_KEY },
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());

Request parameters

Generated from the API schema for this deployment. Conditional parameters apply only when their controlling setting is enabled.

Parameter	Type	Details
`file` Required	string	Short audio or video file. Direct API limit: 30 seconds, 20 MiB.
`diarize`	boolean	Identify speakers in the uploaded recording. Disable for transcription without speaker labels. default: true
`response_format`	string	JSON returns structured transcription. Speaker labels require Separate speakers to be enabled. Plain text contains only the transcript. enum: json, diarized_json, text · default: "diarized_json" All accepted values [ "json", "diarized_json", "text" ]
`keyterms`	array	Optional names, brands or technical terms. In the playground, enter one per line. Up to 20 terms, 30 characters each. Leave empty for ordinary multi-speaker transcription. max 20 items

Complete request schema

{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "file"
  ],
  "properties": {
    "file": {
      "type": "string",
      "format": "binary",
      "description": "Short audio or video file. Direct API limit: 30 seconds, 20 MiB."
    },
    "diarize": {
      "type": "boolean",
      "default": true,
      "description": "Identify speakers in the uploaded recording. Disable for transcription without speaker labels."
    },
    "response_format": {
      "type": "string",
      "enum": [
        "json",
        "diarized_json",
        "text"
      ],
      "default": "diarized_json",
      "description": "JSON returns structured transcription. Speaker labels require Separate speakers to be enabled. Plain text contains only the transcript."
    },
    "keyterms": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 30
      },
      "maxItems": 20,
      "description": "Optional names, brands or technical terms. In the playground, enter one per line. Up to 20 terms, 30 characters each. Leave empty for ordinary multi-speaker transcription."
    }
  }
}

Response schema

The schema below describes the response; optional fields depend on model settings.

View complete response schema

{
  "anyOf": [
    {
      "properties": {
        "text": {
          "title": "Text",
          "type": "string"
        },
        "language": {
          "default": "und",
          "title": "Language",
          "type": "string"
        },
        "language_confidence": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Language Confidence"
        },
        "duration": {
          "default": 0,
          "title": "Duration",
          "type": "number"
        },
        "segments": {
          "items": {
            "$ref": "#/$defs/Segment"
          },
          "title": "Segments",
          "type": "array"
        },
        "words": {
          "items": {
            "$ref": "#/$defs/Word"
          },
          "title": "Words",
          "type": "array"
        }
      },
      "required": [
        "text"
      ],
      "title": "PublicTranscriptionResult",
      "type": "object"
    },
    {
      "type": "string",
      "description": "Plain transcript when response_format=text."
    }
  ],
  "$defs": {
    "Segment": {
      "properties": {
        "id": {
          "title": "Id",
          "type": "string"
        },
        "start": {
          "title": "Start",
          "type": "number"
        },
        "end": {
          "title": "End",
          "type": "number"
        },
        "text": {
          "title": "Text",
          "type": "string"
        },
        "speaker": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Speaker"
        },
        "language": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Language"
        },
        "words": {
          "items": {
            "$ref": "#/$defs/Word"
          },
          "title": "Words",
          "type": "array"
        }
      },
      "required": [
        "id",
        "start",
        "end",
        "text"
      ],
      "title": "Segment",
      "type": "object"
    },
    "Word": {
      "properties": {
        "word": {
          "title": "Word",
          "type": "string"
        },
        "start": {
          "title": "Start",
          "type": "number"
        },
        "end": {
          "title": "End",
          "type": "number"
        },
        "confidence": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Confidence"
        },
        "speaker": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Speaker"
        }
      },
      "required": [
        "word",
        "start",
        "end"
      ],
      "title": "Word",
      "type": "object"
    }
  }
}