As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/qwen3-asr/

# Qwen3-ASR (0.6B / 1.7B) + Qwen3-ForcedAligner

Alibaba (Qwen), Qwen3-ASR family. Status: current. Type: speech and audio. Released: 2026-01-29.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | `Qwen/Qwen3-ASR-1.7B` |  | https://huggingface.co/Qwen/Qwen3-ASR-1.7B |
| Hugging Face | `Qwen/Qwen3-ASR-0.6B` |  | https://huggingface.co/Qwen/Qwen3-ASR-0.6B |
| Hugging Face | `Qwen/Qwen3-ForcedAligner-0.6B` |  | https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B |
| GitHub |  |  | https://github.com/QwenLM/Qwen3-ASR |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: audio
- Output: text
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: apache-2.0

## Where it stands

- Newer speech and audio models in the registry since its release: 69. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from Alibaba: Qwen3-TTS (open weights 0.6B / 1.7B; API qwen3-tts-flash) (2026-01-22) https://postcutoff.com/m/qwen3-tts/
- After it from Alibaba: Qwen3.8-LiveTranslate (Flash Realtime) (2026-09-19) https://postcutoff.com/m/qwen3-8-livetranslate/
- Weights are public under a permissive licence (Apache-2.0).

## What stands out

- 52 languages/dialects incl. singing and music: Language ID + ASR for 30 languages and 22 Chinese dialects, robust on songs/music; built on Qwen3-Omni audio understanding; vLLM batch and streaming inference, timestamp prediction via ForcedAligner. Source: https://github.com/QwenLM/Qwen3-ASR
- Beats Whisper-large-v3 on Chinese: Self-reported WER e.g. AISHELL-2 2.71 vs 5.06 (Whisper-large-v3); Cantonese CV-yue 7.57 vs 11.36 (GPT-4o-Transcribe). Source: https://github.com/QwenLM/Qwen3-ASR

## Notes

Native Transformers (-hf repos) support added 2026-06-26. Hosted ASR is now Qwen-Audio-3.x-ASR (see qwen-audio-3-1-asr).

Apache-2.0 speech recognition models for self-hosting.

Sources: https://github.com/QwenLM/Qwen3-ASR

Model page: https://postcutoff.com/m/qwen3-asr/