Qwen3 ASR

Choose your platform

This add-on has separate macOS and Windows editions. Each page documents the features, settings, requirements, and screenshots for that platform.

• macOS

  v1.1.8

  

  Qwen3-ASR locally through MLX on Apple silicon with downloadable models.

  • Local speech-to-text processing
  • Processing without uploading audio or text
  • Model or runtime downloads managed by TypeWhisper
  • 30 languages plus Chinese dialects
  View this edition: macOS

• Windows

  v1.1.1

  Qwen3-ASR 0.6B or 1.7B offline on the CPU through sherpa-onnx, after a one-time model download.

  • Local speech-to-text processing
  • Processing without uploading audio or text
  • Two INT8 models: Qwen3-ASR 0.6B (recommended, about 879 MB download, about 2 GB RAM) and Qwen3-ASR 1.7B (higher accuracy but slower, about 2.4 GB download, about 3.5 GB RAM)
  • 30 languages, including German, English and Cantonese; without a set language, the model recognizes it automatically
  View this edition: Windows