avatar
SadTalker
Talking-head generator that predicts 3D motion coefficients from audio to animate a single face image.
Levelmodel
Classavatar
Parametersnot in the notes
Contextnot in the notes
Released22 Nov 2022
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Identity
- Developer
- Xi'an Jiaotong University, Tencent
- Family
- not in the notes
- Released
- 22 Nov 2022 sourcesannouncement page
- Weights published
- 8 Apr 2023
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- not in the notes
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- image, audio
- Output
- video
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- MIT License sources
- Access routes
- open weights download, API
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelSadTalkerXi'an Jiaotong University, avatar
SadTalkerXi'an Jiaotong University, avatarR&D TopicsAudio-Driven Talking Heads and Lip-Sync
Use Casesnone recorded
Who Runs Itnone recorded
Sources
- arxiv.org/abs/2211.12194 https://arxiv.org/abs/2211.12194
- huggingface.co/vinthony/SadTalker https://huggingface.co/vinthony/SadTalker
- replicate.com/cjwbw/sadtalker https://replicate.com/cjwbw/sadtalker
- arxiv.org/html/2211.12194 https://arxiv.org/html/2211.12194
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SadTalker", https://aurion.semai.id/models/sadtalker/, records of October 2026.