SpeechSpeech to Text (Async)
API Key not detected. Please configure to use debug features.
*Input Audio

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

Size limit: ≤ 20MB

*Model (model)
Channel (channel)
Business Context (context)0/500
Hotwords (hotwords)0/200
Task Info
Task ID-
File ID-
Trace ID-
Status-
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.hivoice.cn/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": true,
  "enable_speaker": false
}'
Request Body JSON
{
  "model": "u2-asr",
  "file_id": "YOUR_FILE_ID",
  "format": "mp3",
  "channel": 1,
  "enable_itn": true,
  "enable_speaker": false
}