A
Qwen Audio 3.1 ASR
Qwen Audio 3.1 ASR, a transcription model from Alibaba Cloud.
transcriptionModelOverride: { model: "qwen-audio-3.1-asr" }
Qwen·served viaPricing
- Input
- $0.15 / 1M
- Output
- $0.47 / 1M
Specifications
- Released
- September 2026
- Model string
- qwen-audio-3.1-asr-flash-filetrans
- Capabilities
- Multilingual
Parameters
Model options, passed in
transcriptionModelOverride.config.| Parameter | Type | Default | Range / options |
|---|---|---|---|
languageThe spoken language, as a code such as en or es. Leave as Auto to have the model detect it. | Select | — | enesfrdeitpt+7 |
includeSpeakersLabel each sentence with a speaker index when multiple people talk. Keep the audio under 2 hours. | Select | no | yesno |
includeWordTimingsAdd per-word start/end times and confidence inside each transcript segment. Increases the size of the result considerably. | Select | no | yesno |
subtitlesAlso return the transcript as a subtitle file, SRT or WebVTT, timed to the audio. | Select | — | srtvtt |
Use this model
await mindstudio.transcribeAudio({ audioUrl: "...", transcriptionModelOverride: { model: "qwen-audio-3.1-asr", config: { includeSpeakers: "no", includeWordTimings: "no", }, }, });