How do I run AI Talking Avatar Generator?

Try it free in the playground on this page, or call it from your own app with one API key — async, synchronously, or streamed. No setup or servers to manage.

How much does AI Talking Avatar Generator cost?

Runs are billed usage-based from your workspace balance — the cost of a run is the model and media usage it incurs, with no per-call platform fee. Every run reports its exact cost.

Can I use AI Talking Avatar Generator in my own product?

Yes — it's API-native. Embed it behind your own UI and call it from any language; your users never have to leave your product.

puras / Avatar Studio

AI Talking Avatar Generator

An AI talking-head video generator: turn a text script — and an optional presenter photo — into a lip-synced talking-avatar video that reads your exact words to camera, in the language you choose. No camera, talent, or editing — a finished clip ready for ads, explainers, or social.

Input

Output

Presenter photo + script → talking video

~$1.10 per clip·Run it free in the playground, then call it from your app.

Run it View the API

Input

Output

Presenter photo + script → talking video

No inputs handy? Try one of these

Output appears here — run the skill, or pick an example to see a real input/output pair.

For developers

Run it from your own stack.

This skill is an API. One call runs the whole pipeline server-side as a long-running job and returns the result — from Python, plain HTTP, or an MCP-connected coding agent.

API access — MCP · Python SDK · cURL · JSON schemas

MCP· recommended for coding agents

claude mcp add --transport http puras https://mcp.puras.co/mcp

OAuth on first call — no key to paste. Then ask the agent to run talking-avatar from skill puras/avatar-studio.

CLI

pip install puras
puras login            # or set PURAS_API_KEY
puras run puras/avatar-studio/talking-avatar -i key=value

Python SDK

import puras

client = puras.Client()   # PURAS_API_KEY from env
result = client.run("puras/avatar-studio/talking-avatar", {"voice":"auto","script":"Big news — we just shipped dark mode. Open Settings, tap Appearance, and pick Dark. Your eyes will thank you tonight.\n","avatar_image":"https://uozfqcfhlhugotnevscg.supabase.co/storage/v1/object/public/puras-public-skills/talking-avatar/dark-mode-presenter.jpg"})

HTTP API· wait=true blocks until the job finishes

curl -X POST "https://api.puras.co/v1/jobs?skillpack=puras/avatar-studio&wait=true" \
  -H "Authorization: Bearer $PURAS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"skill":"talking-avatar","inputs":{"voice":"auto","script":"Big news — we just shipped dark mode. Open Settings, tap Appearance, and pick Dark. Your eyes will thank you tonight.\n","avatar_image":"https://uozfqcfhlhugotnevscg.supabase.co/storage/v1/object/public/puras-public-skills/talking-avatar/dark-mode-presenter.jpg"}}'

Input schema (JSON Schema)

{
  "type": "object",
  "required": [
    "script"
  ],
  "properties": {
    "look": {
      "type": "text",
      "maxLength": 400,
      "description": "Optional steer for the generated presenter and setting. Ignored with avatar_image."
    },
    "voice": {
      "enum": [
        "auto",
        "warm_female",
        "warm_male",
        "energetic_female",
        "energetic_male",
        "calm_narrator",
        "authoritative_male"
      ],
      "type": "string",
      "default": "auto",
      "description": "Voice persona. `auto` fits it to the script."
    },
    "script": {
      "type": "text",
      "maxLength": 1000,
      "minLength": 2,
      "description": "The exact words spoken, verbatim. Plain prose, no SSML."
    },
    "language": {
      "type": "string",
      "maxLength": 12,
      "description": "Optional language code (e.g. \"en\", \"tr\"). Empty = auto-detect."
    },
    "aspect_ratio": {
      "enum": [
        "9:16",
        "1:1",
        "16:9"
      ],
      "type": "string",
      "default": "9:16",
      "description": "Output frame. Honored on the generated-portrait path only — ignored when you supply avatar_image (the photo's framing wins)."
    },
    "avatar_image": {
      "type": "image",
      "description": "Optional presenter portrait. Clear, front-facing, mouth visible."
    }
  }
}

Output schema (JSON Schema)

{
  "type": "object",
  "properties": {
    "video": {
      "type": "video",
      "description": "The rendered talking-avatar clip (lip-synced narration). The playground renders it with a <video> player.\n"
    }
  }
}

Spec Docs

Call AI Talking Avatar Generator from your app.

Run it free in the playground above, then wire it in with one call — from Python, TypeScript, or your coding agent over MCP. Every run returns an exact cost receipt.

Run it Read the quickstart

Every run is billed to the cent — see pricing.