Lip Sync — Automatic Lip-Syncing

Please note that Audio Analysis can take time, depending on your computer.

Lip Sync is a powerful Blender add-on that brings automated lip-sync animation to your characters.

In just a few clicks, analyze an audio clip and generate phoneme-based keyframes for your character's mouth movements. No manual keyframing needed — Lip Sync does the heavy lifting for you.

Key Features

• Automatic phoneme extraction from voice audio
• Supports 25+ languages, including English, French, Spanish, German, Russian, Hindi, Mandarin, and more
• 3D Shape keys animation
• 2D spritesheet mouth shape animation
• Upcoming support for Pose Library animation
• Cached models for faster re-analysis and offline use
• Easily integrates with Blender’s Video Sequencer

Technologies Used

Lip Sync uses a robust pipeline of open-source speech and phoneme processing tools to ensure both accuracy and performance:

• Vosk
  Offline speech recognition engine that transcribes audio into text and phonemes.
  Bundled for Windows, macOS, and Linux

• eSpeak NG
  Lightweight and fast phoneme synthesizer that converts text into timed phoneme sequences.

A custom build is bundled with the add-on for all platforms

• Phonemizer
  Linguistically accurate phoneme segmentation across multiple languages

Ensures correct mouth shapes in context-sensitive languages

Efficient Model Management

On first use, the add-on downloads the required Vosk model for the selected language.
These models are then cached locally to your system, so:

• No repeated downloads
• Faster future analyses
• Fully offline functionality after setup

You only download what you need, when you need it.

Try it today and let your characters speak!

Video Trailer Attribution:

• Animated Platformer Character by Quaternius
• Wall Art 06 by Jarlan Perez CC-BY via Poly Pizza