TimoBolkart/voca

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1263 stars · 277 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

VOCA is a speech-driven 3D facial animation framework that synthesizes realistic character face animations from an arbitrary speech signal and a static character mesh. It is the official research code accompanying the CVPR 2019 paper 'Capture, Learning, and Synthesis of 3D Speaking Styles', built on Python and TensorFlow.

Use cases

• animate a 3D character mesh from an audio speech clip
• generate talking-head facial animation from voice recordings
• research speech-driven 3D face animation
• apply one trained model to animate multiple character identities
• produce 3D speaking-style animation sequences for games or films
• work with the FLAME morphable face model

When to choose

• you need research-grade speech-to-3D-face animation with a pretrained model
• you work with FLAME topology meshes and TensorFlow 1.x
• you want to reproduce or build on the VOCA/VOCASET CVPR 2019 work

When to avoid

• you need production-ready software with an active support community
• you cannot use legacy TensorFlow 1.x and Python 3.6/3.7 environments
• you need real-time lip sync in a game engine rather than offline mesh animation
• you require a permissive license - the repo has no license file

Facets

library · maturity maintenance

machine-learning audio-processing image-processing animation computer-vision machine-learning deep-learning python speech-driven-animation 3d-face facial-animation morphable-model flame tensorflow research-code talking-heads computer-graphics linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="TimoBolkart/voca")