vsref

SadTalker Review

OSS

Landmark academic photo-to-talking-head model; single-image + audio in, stylized head/expression motion out, not a full body/avatar platform.

See pricing

Facts verified Aug 24, 2026Website →

What we know about SadTalker

SadTalker sits in the ai avatar video category, where it is landmark academic photo-to-talking-head model; single-image + audio in, stylized head/expression motion out, not a full body/avatar platform. We keep this SadTalker profile grounded in primary sources, each fact dated to when we last confirmed it.

SadTalker does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current SadTalker quote, it is the fastest way for us to close that gap.

On capabilities, SadTalker covers self-hostable. Each of those is verified against SadTalker's own docs or dashboard, not marketing copy.

In total we track 4 verified facts for SadTalker today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the SadTalker fact sheet below.

Reviewed by vsref Editorialfacts verified Aug 24, 2026Methodology →

Fact sheet

Compliance & trust
Compliance & trust facts
LicenseApache-2.0Aug 24
Self-hostable✓ YesAug 24
Commercial
Commercial facts
GitHub stars14,000Aug 24
Last release2023-06-05 dateAug 24

Considering a switch? Best SadTalker alternatives →

SadTalker head-to-head

SadTalker vs Wav2Lipwon 5 · lost 0 · tied 1
BudgetwonConversational AvatarstieDevelopers & APIwonMarketing & UGC AdswonSales OutreachwonTraining & L&Dwon