Mark McKayParrot Lipsync is a Blender add-on that automates the generation of lip-sync data from audio tracks. It supports both 2D and 3D animations and utilizes OpenAI’s Whisper library to convert spoken audio to text and Gruut to translate this text into phonemes. These phonemes are then used to create accurate mouth position keyframes.
Key Features:
- Automated Lip-Sync Animation: Converts spoken audio into lip-synced animations automatically.
- Multilingual Support: Capable of handling various common languages, though it excludes East Asian languages using kanji.
- Editable Mouth Position Definitions: Users can modify or completely customize the mouth position settings through an included JSON file.
- Integration with Advanced Libraries: Uses Whisper for accurate speech recognition and Gruut for detailed phoneme analysis.
