ReferenceAsk
Back to Remy
Remy Reference/models/Qwen3 ASR 1.7B
D

Qwen3 ASR 1.7B

Qwen3 ASR 1.7B, a transcription model from DeepInfra.
transcriptionModelOverride: { model: "qwen3-asr-1.7b-deepinfra" }
Qwen·served viaDeepInfra·Released 2026
Pricing
Per second
$0.0000075
Per minute
$0.00045
Per second
$0
Per minute
$0
Specifications
Released
2026
Model string
Qwen/Qwen3-ASR-1.7B
Capabilities
Open sourceMultilingual
Parameters
Model options, passed in transcriptionModelOverride.config.
ParameterTypeDefaultRange / options
language
The spoken language, as a code such as en or es. Leave as Auto to have the model detect it.
Select—enesfrdeitpt+7
subtitles
Also 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: "qwen3-asr-1.7b-deepinfra",
  },
});