Video model · MultiTalk
Infinitalk
Turn a photo and an audio clip into a talking avatar
What is Infinitalk?
Infinitalk is an audio-driven talking-avatar model. Give it a portrait and an audio track and it animates the face to speak in sync, with the clip length following the audio.
Capabilities
- Animate a photo into a talking avatar
- Lip-sync the face to any audio track
Infinitalk on Melius
Melius runs Infinitalk alongside every other major image, video, audio, and text model, so you can generate with it, compare it against the field, and let the Mel agent route to it automatically — all on one infinite canvas. You only pay for what you generate.
Frequently asked questions
What is Infinitalk?
Infinitalk is an audio-driven talking-avatar model. Give it a portrait and an audio track and it animates the face to speak in sync, with the clip length following the audio.
How do I use Infinitalk on Melius?
Open Melius, add a node, and pick Infinitalk from the model picker — or just describe what you want and let the Mel agent route to it. You only pay for what you generate.