Qwen Audio 3.1 ASR
Transcription by Qwen
Qwen
Alibaba CloudReady to build with Qwen Audio 3.1 ASR?
Get Started FreeParameters & options
The spoken language, as a code such as en or es. Leave as Auto to have the model detect it.
Label each sentence with a speaker index when multiple people talk. Keep the audio under 2 hours.
Add per-word start/end times and confidence inside each transcript segment. Increases the size of the result considerably.
Also return the transcript as a subtitle file, SRT or WebVTT, timed to the audio.
Explore similar models
QwenQwen3 ASR 1.7B
Qwen3 ASR 1.7B is an open-source multilingual speech-to-text model developed by Qwen with 1.7 billion parameters.
QwenQwen3 ASR 0.6B
QwenQwen Audio 3.0 TTS Plus
MistralVoxtral Mini Transcribe 3
GoogleGemini 3.5 Transcribe
ElevenLabsScribe v2
Scribe v2 is a speech-to-text transcription model from ElevenLabs that supports speaker identification.
Start building with Qwen Audio 3.1 ASR
No API keys required. Create AI-powered workflows with Qwen Audio 3.1 ASR in minutes — free.