Build live avatars into your product with Interactive Avatar API
Build real-time, lip-synced avatar experiences into your web product while keeping control of your LLM and speech stack with Interactive Avatar API.
See what Synthesia can do for you
Give your product a real-time avatar that listens, responds, and lip-syncs on the fly while you keep full control of the AI behind it. And the best part? You get 500 free minutes to try it out.
What's new
- Bring your own LLM and speech stack: Your model, your knowledge base, your logic — Synthesia only renders the avatar. Don't want to bring your own text-to-speech? Use ours, built into the plugin at no extra cost.
- Drop it into your existing agent: Connect through the official
livekit-plugins-synthesiaplugin — a couple of lines of code, and the avatar joins your LiveKit room as a live participant. - Natural, interruptible conversations: Turn-taking and mid-response interruptions are supported out of the box, so people can talk over the avatar the way they would a real person.
- Use Express 2 avatars, including synthetic and cartoon avatars
Teams are already using this for always-on customer support that hands off to a human when needed, sales reps that qualify leads and book demos, training, and kiosks or lobby screens that greet and guide visitors in person.
Get your API key and check out the documentation to get started.
More updates
Improve videos created by Assistant with curated b-roll
The Assistant now adds curated AI video b-roll featuring your Avatar—automatically matched to your scene, delivered in seconds, and free on all plans.
Get the skills, insights, and support to help you scale
