HeyGen launches Avatar 6 model for more natural gestures in AI avatar video
AI video company HeyGen has launched Avatar 6, a new model for generating video of a person's digital avatar. The audio-driven model reads a script and the way it is spoken and generates matching gestures and expressions, which HeyGen says addresses the repetitive, unnatural movement common in AI avatar video.
The model learns from footage of each user and can build an avatar from as little as 30 seconds of video. Users can also connect YouTube, Instagram or TikTok accounts to use existing footage. HeyGen says the model's runtime context window grew about tenfold, from roughly 3 to 30 seconds, giving more varied movement, better lip sync and native 2K output. Existing personal avatars are upgraded automatically, and the model is available in HeyGen, through its API and on some third-party platforms.
HeyGen says that in its own Turing-style testing, 84% of participants rated the avatar as equally realistic as the real person, and that the model ranked first in New Measure's Avatar Arena, a blind head-to-head comparison.
The company requires live identity verification and explicit consent before creating realistic avatars of real people, and says realistic videos of real people stay on HeyGen's own platform, according to the announcement.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Daily AI Brief.
Also, consider following us on social media:
Daily AI Brief
Daily report covering major AI developments and industry news, with both top stories and complete market updates
Market report
2025 Generative AI in Professional Services Report
Thomson Reuters
This report by Thomson Reuters explores the integration and impact of generative AI technologies, such as ChatGPT and Microsoft Copilot, within the professional services sector. It highlights the growing adoption of GenAI tools across industries like legal, tax, accounting, and government, and discusses the challenges and opportunities these technologies present. The report also examines professionals' perceptions of GenAI and the need for strategic integration to maximize its value.
Read moreYou may also like
Google DeepMind Releases Genie 4 World Model With Audio and Live Steering
Tohoku University AI makes digital humans move as they speak
Tencent Releases Hy-Nomas for Interactive Video World Generation
Pixazo Launches Agent P for Conversational Media Creation
Pika Labs Releases Open Weight H3 Flex Video Model
Daily AI Brief: the AI news that matters, in your inbox.