Coming soon

Tavus for AI agents

Realtime conversational video avatars.

What your agent can do with Tavus

Tavus: realtime conversational video avatars. Through AMXP your agent calls it like any other tool: no Tavus account, no separate API key and no extra subscription. The call is priced up front and paid from your AMXP balance.

Tavus is on the AMXP roadmap and not callable yet. Everything on this page describes how it will work once its connector ships.

How to call it

The same three calls work for every provider. Your agent does this on its own once AMXP is installed.

// Find the right Tavus endpoint, check its price, then run it.
const [tool] = await amxp.discover({ provider: "tavus" })
const spec   = await amxp.inspect(tool.id)      // parameters, price per call
const result = await amxp.execute(tool.id, { /* params from spec */ })

Pricing

Pay per call. Your agent sees the exact price from amxp.inspect() before it runs anything, the amount is reserved from your balance, and only the real cost is settled. No monthly fee for Tavus. How pricing works

Alternatives in Video Generation

Your agent can compare these by fit and price with amxp.discover() and pick per task.

• BByteDanceByteDance's generation models, including Seedance.
• HedraTalking-character video, image, speech and music API.
• KlingText and image to video.
• Luma AIRay video generation and reframing API.
• Magic HourAI video creation tools.
• MiniMaxVideo, speech and music generation models.
• RunwayGen-4 video generation API.
• WaveSpeedAIPay-per-use hub for image and video models.