/logo.webp){kind=logo}
About
SadTalker is an AI digital-actor and lip-sync tool. Open-source photo-plus-audio talking head you can self-host.
Our take — SadTalker for short drama
SadTalker — a CVPR 2023 project from Xi'an Jiaotong University and Tencent AI Lab — turns one portrait photo plus an audio track into a talking head, using 3DMM motion modeling with an optional GFPGAN face enhancer. For short drama our honest read: it's the classic budget primitive for narrator inserts and stylized flashback faces, not scenes carrying emotional weight.
Against LivePortrait, SadTalker is audio-driven where LivePortrait is performance-driven — no actor required, just a voice file, which suits fully synthetic pipelines. It's Apache 2.0 and self-hosts fully offline, a real privacy plus for unreleased scripts. But major updates date to 2023, so we'd treat it as stable-but-aging; newer hosted lip-sync like Sync will out-render it.
Fully synthetic pipelines needing offline, audio-driven talking heads from a single photo at zero license cost.
Major updates stalled since 2023; output quality trails current hosted lip-sync tools.
- Photo plus audio to talking head
- 3DMM motion, GFPGAN enhancement
- Apache 2.0, fully offline
- Stable Diffusion WebUI extension
Popularity & traffic
Stars and commit dates come from the public GitHub API, updated 2026-07-07.
How short-drama creators use it
Used to create or drive an on-screen character, or to re-mouth filmed actors when dubbing into a new language.
FAQ
What is SadTalker?
SadTalker is an AI digital-actor and lip-sync tool. Open-source photo-plus-audio talking head you can self-host.
Is SadTalker free?
Yes, SadTalker is free to use.
Does SadTalker support vertical 9:16?
SadTalker isn't vertical-first; check its site to confirm 9:16 support.
What are the alternatives to SadTalker?
Alternatives include HeyGen, Sync, Synthesia, D-ID.
Alternatives to SadTalker
15 more digital actors tools
Visiting opens the tool's official site (with a referral tag).
← All tools