MetaPerson and Lipsync

MetaPerson avatars are designed to seamlessly integrate with leading lipsync technologies, enabling realistic and expressive speech synchronization for your projects. Whether you're working in Unity, Unreal Engine, or another platform, MetaPerson provides the flexibility to enhance your avatars with high-quality lipsync capabilities. For detailed implementation, refer to the sections below.

MetaPerson avatars support a comprehensive viseme set, 'visemes_15', which includes a total of 14 visemes and 1 additional blendshape for Laughter. This set is identical to the Oculus Lipsync visemes, making it straightforward to integrate with popular lipsync tools.

Here is the complete list of supported visemes:

• PP
• FF
• TH
• DD
• kk
• CH
• SS
• nn
• RR
• aa
• E
• ih
• oh
• ou
• Laughter (blendshape)

For more details, refer to the official Oculus Lipsync documentation.

📄️ SALSA lipsync

Add real-time lip-sync to MetaPerson avatars with SALSA LipSync for Unity — drive natural mouth movement from audio, with a video walkthrough.

📄️ Oculus Lipsync UE

Add realistic lip-sync to MetaPerson avatars in Unreal Engine using Oculus Lipsync — a step-by-step integration guide with a video walkthrough.

📄️ Oculus Lipsync Unity

Add realistic lip-sync to MetaPerson avatars in Unity using Oculus Lipsync — a step-by-step integration guide with a video walkthrough for your project.