Alibaba · Qwen · ASR

Qwen Audio 3.0 ASR Flash

Multilingual audio understanding and fast speech-to-text transcription.

qwen-audio-3-asr-flash-sg

$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
streaming output
word timestamps
segment timestamps
hotwords

Automatic language detection: supported.

API endpoint

POST https://api.speechinfra.com/v1/inference/qwen-audio-3-asr-flash-sg

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

cURL

curl --fail-with-body "https://api.speechinfra.com/v1/inference/qwen-audio-3-asr-flash-sg" \
  -H "Authorization: Bearer $SPEECH_API_KEY" \
  -F "file=@clip.wav"

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/qwen-audio-3-asr-flash-sg",
        headers=headers, files={"file": ("clip.wav", audio, "audio/wav")},
        data={}, 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({})) form.set(key, value);
const response = await fetch("https://api.speechinfra.com/v1/inference/qwen-audio-3-asr-flash-sg", {
  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.
`language_hints`	array	Leave empty for automatic detection. max 4 items
`vocabulary_id`	string	max 200 chars
`vocabulary`	object	JSON object mapping hotwords to weights 1-5 or 50. max 2000 entries
`context`	string	Recognition context; the provider limit is 400 characters for one context turn. max 400 chars

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."
    },
    "language_hints": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "zh-CN",
          "en",
          "ja",
          "ko",
          "vi",
          "th",
          "id",
          "ms",
          "tl",
          "hi",
          "ar",
          "fr",
          "de",
          "es",
          "pt",
          "ru",
          "it",
          "nl",
          "sv",
          "da",
          "fi",
          "no",
          "el",
          "pl",
          "cs",
          "hu",
          "ro",
          "bg",
          "hr",
          "sk"
        ]
      },
      "maxItems": 4,
      "description": "Leave empty for automatic detection."
    },
    "vocabulary_id": {
      "type": "string",
      "maxLength": 200
    },
    "vocabulary": {
      "type": "object",
      "additionalProperties": {
        "type": "integer",
        "enum": [
          1,
          2,
          3,
          4,
          5,
          50
        ]
      },
      "maxProperties": 2000,
      "description": "JSON object mapping hotwords to weights 1-5 or 50."
    },
    "context": {
      "type": "string",
      "maxLength": 400,
      "description": "Recognition context; the provider limit is 400 characters for one context turn."
    }
  }
}

Response schema

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

View complete response schema

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