Apache-2.0 audio-driven generator: image-to-video talking avatars and video-to-video dubbing of unlimited length
InfiniteTalk is listed under AI Avatars & Headshots, in the Content & Media Generation category on Flocci AI Tools. Apache-2.0 audio-driven generator: image-to-video talking avatars and video-to-video dubbing of unlimited length. It is free, with no paid plan attached, and it lives at github.com.
InfiniteTalk is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 397 entries on Flocci AI Tools with no upgrade path built in.
InfiniteTalk needs to be installed or self-hosted — it doesn't run in a browser tab. It is available on self-hosting.
InfiniteTalk does 3 things the catalog singles out: Apache-2.0 audio-driven generator: image-to-video talking avatars and video-to-video dubbing of unlimited length; syncs lips, head, body posture and expressions; 480p/720p; runs on wan-based weights, comfyui supported.
LivePortrait (Kuaishou) is the closest free alternative: it sits in the same AI Avatars & Headshots sub-category and is free. MuseTalk (Tencent) and Vidnoz AI also start free. The full list is on the alternatives page.
See the full list →