Speech›Speech to Text (Async)
API Key not detected. Click "Configure API Key" in the top-right corner before using the playground.
*Input Audio

Supported formats: mp3,opus,wav,amr,m4a,ogg

Size limit: ≤ 80MB

*Model (model)
Channel (channel)
Task Info
Task ID-
File ID-
Trace ID-
Status-
Recognition Result
Result will show here
Usage Guide
Async speech transcription is suitable for transcribing long audio.
Supports Mandarin, Cantonese, English, and 10+ languages and dialects.
Supports speaker diarization, smart sentence segmentation, and punctuation prediction.
API Reference
CURL
curl -X POST "https://maas-api.unisound.com/v1/audio/asr/tasks" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "u2-asr",
  "file_id": "YOUR_FILE_ID",
  "format": "mp3",
  "channel": 1,
  "enable_itn": false,
  "enable_speaker": false,
  "enable_auto_lang": true
}'
Request Body JSON
{
  "model": "u2-asr",
  "file_id": "YOUR_FILE_ID",
  "format": "mp3",
  "channel": 1,
  "enable_itn": false,
  "enable_speaker": false,
  "enable_auto_lang": true
}