Qwen · Transcription model

Qwen3 ASR Flash

qwen/qwen3-asr-flash-2026-02-10

Transcription

Released May 14, 2026

Qwen3-ASR-Flash is Alibaba's automatic speech recognition service, built on the Qwen3-Omni foundation and trained on tens of millions of hours of multimodal speech data. The model handles 11 languages —...

Specifications

Input: wav, mp3, flac, m4a, ogg, webm, aac, opus · base64 JSON, multipart file or URL · up to 25 MB
Output: text; verbose_json adds language, duration, segments and word timestamps
Billing: per second of audio

Use it

POST /api/v1/audio/transcriptions · MCP transcribe · full reference

curl https://omnirail.org/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $OMNIRAIL_KEY" \
  -F model=qwen/qwen3-asr-flash-2026-02-10 \
  -F file=@meeting.mp3