kkakkkka/MambaTalk

[NeurlPS-2024] The official code of MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models

41
/ 100
Emerging

This tool helps animators and content creators automatically generate realistic human body gestures, including facial expressions, hand movements, and full-body motion, directly from audio recordings of speech. You provide a speech audio file and optionally its corresponding text transcript, and it outputs a 3D animation sequence of a person naturally gesturing along with the speech. This is ideal for professionals creating virtual assistants, animated characters, or digital doubles.

Use this if you need to quickly and efficiently animate natural, holistic human gestures for a digital character based on spoken audio.

Not ideal if you need fine-grained control over specific gesture styles or highly nuanced, non-speech-driven movements, as this is primarily an automated synthesis tool.

character-animation virtual-assistants content-creation digital-humans motion-synthesis
No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

76

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Jan 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kkakkkka/MambaTalk"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.