Download the Rhubarb Lip Sync executable and the Blender addon.

Sound travels slower than light, and human brains anticipate speech visually. Try grabbing all your generated mouth keyframes in the dopesheet and shifting them 1 or 2 frames backward (so they happen slightly before the audio plays) . This makes the lip-sync feel significantly more natural to the viewer.

Download the latest version of the from GitHub.

: When animating 2D mouth shapes (visemes), set your keyframe interpolation to

In this post, we’ll walk through how to set up and use the Auto Lip Sync add-on to bring your characters to life in minutes. 1. Enable the Native Add-on

# Reset it to 0.0 a few frames later so it doesn't stay stuck open key_blocks[viseme].value = key_blocks[viseme].keyframe_insert(data_path= , frame=frame + # To test: select your mesh and run # apply_lip_sync(bpy.context.active_object, lip_sync_data) Use code with caution. Copied to clipboard 5. Advanced Considerations for Polish Dynamic Falloff:

: A robust, cross-platform extension that uses the Vosk engine for offline speech recognition. It supports over 25 languages and works with both 3D shape keys and 2D sprite-based animations.

Right-click the slider of that shape key and select Insert Keyframe . Open the Graph Editor window.

For precise speech recognition, you need tools that analyze phonemes. Several add-ons bridge the gap between external speech-to-text engines and Blender. Rhubarb Lip Sync (Open-Source Standard)

module to call the Rhubarb executable in the background. Rhubarb will output a JSON file or TSV with timestamps and corresponding mouth shapes (e.g., 0.15s: Mouth Shape A 0.45s: Mouth Shape B Step 3: Map Data to Blender Animation

However, it's important to understand what auto lip sync can and cannot do. The best results come from treating automation as a powerful starting point—a first pass that you then refine and polish manually to add nuance, emotion, and personality.

Blender 4.1 to 4.5, 8GB+ RAM recommended, approximately 5GB storage space for AI models, internet connection for initial setup

It uses both the audio file and a text transcript to ensure the mouth hits "hard" consonants perfectly.

Rhubarb relies on 6 to 9 specific mouth shapes. You must create these Shape Keys on your character model first: (closed mouth, neutral) B (slightly open mouth, teeth together like 'S' or 'T') C (open mouth, teeth apart like 'EH' or 'AE') D (wide open mouth like 'AA') E (slightly closed mouth, rounded lips like 'O') F (pursed lips like 'UW' or 'W') G (teeth touching lower lip like 'F' or 'V') Step 2: Setting up the Addon Download the Rhubarb Lip Sync Blender Addon from GitHub. Install it via Edit > Preferences > Add-ons > Install .

Apps like Live Link Face (by Epic Games) or Face Cap record your face while you speak and stream the 52 ARKit blendshapes directly into Blender.

is a command‑line tool created by Daniel S. Wolf that automatically creates mouth animation from voice recordings. It's widely considered the gold standard for automated lip sync, and several Blender add‑ons have been built to integrate it seamlessly.

No matter which automated tool you choose, your character model must be properly prepared. Automation scripts cannot guess how your character's mouth moves without predefined targets. Step 1: Create Your Shape Keys