Here's a uv one-liner that downloads and runs the MLX model against a local mp3 file uv run –with mlx-audio python -m mlx_audio.stt.generate
–model mlx-community/VibeVoice-ASR-4bit
–audio lenny.mp3 –output-path lenny
–format json –verbose –max-tokens 32768

→ View original post on X — @simonw,