Generate lip-sync animations directly from audio clips in Blender. All processing is done locally — no account, subscription, or network access required.
How it works
Drop an audio clip into the Blender video sequencer and generate ARKit blendshape keyframes for any rigged mesh. Supports multilingual audio with strongest performance in English and Mandarin Chinese.
Requirements
- Blender 3.1–3.6 or 4.0–4.2
- Mesh rigged with ARKit blendshapes
- Audio file (WAV, MP3, etc.)