Launching today
VisoTalk
An agent skill for explainer videos
1 follower
An agent skill for explainer videos
1 follower
VisoTalk is an open-source agent skill for explainer videos. Every animation hangs on the word that says it, not on a second, so you can rewrite a line, change the voice or translate the film and the picture follows. Plays on the web, renders to video files.
Free
Launch Team
Framer AI AgentsDesign and publish professional sites with AI
Promoted
Hi Product Hunt 👋
I built VisoTalk because AI agents make great videos until the narration changes. Most tools pin every animation to a second, so rewrite one sentence and everything after it lands a beat late.
VisoTalk has one rule: narration is the new timeline. Each animation hangs on the word that says it. The engine speaks the script, times every word and solves the timeline from them, so you can rewrite a line, change the voice or translate the whole film, and the picture follows.
A film is one doc.tsx your agent writes. It plays live in the browser and renders to MP4. This launch video was made with it.
It's open source (MIT), works with Claude Code, Codex and other agents.
I'd love to hear what you'd make with it, and where it breaks.