HeyGen Launches Avatar 6: 84.4% Indistinguishable From Real Footage
HeyGen · x · 2026-11-18
HeyGen has launched Avatar 6, its latest AI avatar model, focused on performing like the real person: instead of recycling the same gestures, it reads the script and matches context-appropriate expressions, pointing, counting, and directional motion, with optional prompt-level control over emotion and gestures.
Key numbers: every frame is native 2K, and side-by-side with real footage the avatar is 84.4% indistinguishable, up from 44.4% for the previous Avatar V. HeyGen claims first-take results with no tweaking. The product also ships as a ChatGPT plugin, offers an API, and a live demo is scheduled for 11/18 at 10am PT.
Related event: HeyGen Launches Avatar 6, Blurring the Line Between Digital and Real Humans(3 posts)→
More from Multimodal
- Selective-color portrait with Gemini 4 Argon: peeled layer revealing vivid eyes — AnswerVinod · 2026-11-18
- HeyGen launches Avatar 6: 84% of people can't tell its avatars from real humans — HeyGen · 2026-11-18
- Midjourney's Edit Model Now Supports Moodboards, Style Codes and Style References — midjourney · 2026-11-18
- MOSS-Image FP16-fixed weights bring speed boost to aging Turing GPUs — mkrGG · 2026-11-18
- One JSON prompt, three tools: Claude vs ChatGPT vs Figma Make for pixel-perfect UI — Tegadesigns · 2026-11-18
- Kling Motion Control Keeps Importing Reference Image Background Into Generated Videos — Flat-Scholar1878 · 2026-11-18