AutoPersonify

For developers

An AI avatar API built to be easy for developers and their AI tools

Eight endpoints, one error shape, an OpenAPI spec and a copy-ready prompt your AI coding tool can follow on its own.

AutoPersonify's API covers the whole avatar video flow: GET /me for the allowance, /presenters and /twins to pick who speaks, POST /twins to request a new twin, and /videos to make and track videos.

How it works

  1. 1Create a keyIn AutoPersonify go to Integrations, then Developer API, and create a key. It is shown once.
  2. 2Store it server-sideSave it as a secret such as AUTOPERSONIFY_API_KEY and call the API only from server code.
  3. 3Check the allowanceGET /me returns the plan, video seconds left and twin slots, so your app can tell the user what they can do.
  4. 4Build the flowUse the OpenAPI spec or the copy prompt to build twin requests, a picker, progress screens and a video library.

The API calls

curl https://autopersonify.com/api/v1/me -H "Authorization: Bearer $AUTOPERSONIFY_API_KEY"
# -> { "plan": "Free", "video_seconds_remaining": 180, "twins_used": 0, "twins_allowed": 1, "upgrade_url": "..." }

Full reference: developer docs, OpenAPI spec, markdown guide.

What you can build

  • A video library page in your app
  • Twin creation inside your onboarding
  • Automated video jobs from your CRM or database

Honest limits

  • Videos take a few minutes to make, usually 2 to 10. Poll every 10 to 15 seconds or use webhooks.
  • Every finished video uses the account's video minutes. When they run out, the API returns allowance_exceeded with a message you can show as it is.
  • Call the API from server code only. Never put the key in browser code.

Questions people ask

Is there an OpenAPI spec?

Yes, at https://autopersonify.com/openapi.json. A full markdown guide is at https://autopersonify.com/developers.md.

What does an error look like?

Every error is { error: { code, message, user_message, action, retryable } }. user_message is written for the end user and can be shown as it is.

Are there rate limits?

Yes, per key, plus a daily video limit and a concurrency limit. A 429 response includes Retry-After.

Related

Last updated 2 October 2026.

Start free, no card required

3 free video minutes and one twin. Create an API key in Integrations and paste the prompt into your AI tool.

Start freeRead the API docs