Panim Lipsync
What does this addon do?
PAnim LipSync automatically creates lip-sync animations for your 3D characters in Blender using AI speech recognition. Simply load an audio file and the addon generates mouth movements that closely match the speech.
What are the system requirements?
Blender 4.1 to 4.5 (Current Last Version), 8GB+ RAM recommended, Up to ~5GB storage space for AI models (PRO Version).
Do I need an internet connection?
Only for the initial setup to download dependencies and AI models. After that, everything works offline locally on your computer.
What audio formats are supported?
WAV, MP3, OGG, FLAC, M4A, and AAC files are all supported.
What shape keys do I need on my character?
The addon needs these shape keys:
PRO: Mouth_Shape_A/E/I/O/U/M/B/P/F/L
Lite: Mouth_Shape_A/E/I/O/U/M/
What if my character doesn't have the standard shape keys?
If your character has no shape keys, the addon can auto-create them for you to modify each one. If you have shape keys with different names, use the custom mapping feature to connect your existing shape keys to the standard phonemes.
Can I use it with rigged characters (bones)?
Yes! The addon supports both shape key animation and bone-based animation modes (using actions).
Can I animate multiple characters at once?
Yes, the batch processing mode lets you animate multiple characters with different audio clips simultaneously. (PRO)
How long does processing take?
Depends on your hardware, model size, and audio length. First-time processing is slower as it loads the AI model, then subsequent processing is much faster. Times can range from seconds to minutes depending on your system.
Does it work with different languages?
Yes, it supports 20+ languages including English, Spanish, French, German, Chinese, Japanese, and many more.
The "Install Dependencies" button fails. What should I do?
Run Blender as Administrator, check your internet connection.
Discover more products like this
mouth shape keys animation speech recognition beginner-friendly Time-saving Facial Animation phonemes lipsync automation visemes Speech generation rigging