Creatify API: AI avatar videos, Aurora lip sync and credits

The Creatify API is a REST API for marketing video. It makes AI Avatar videos of a stock or custom persona speaking your text or audio, Aurora talking-head videos from one photo plus an audio clip, and short video ads from a product URL. Access needs a Creatify API plan, and each generation spends credits: 5 credits per 30 seconds for AI Avatar and URL to Video, 1 credit per second for Aurora.

Creatify's facts below come from its own API docs, read on 2026-09-28 and linked under Sources. The per-second alternative at the end comes from Sume's Generate avatar video docs and the Sume API reference.

What can you make with the Creatify API?

Creatify's FAQ lists URL-to-video, AI avatar lip sync, Aurora image-to-video, custom templates, product video, AI Shorts, AI Editing and text to speech. The avatar and lip-sync endpoints are these:

How do you call it?

• Send two headers, X-API-ID and X-API-KEY, shown under API Dashboard in your Creatify account. Creatify says to keep the key out of client-side code.
• Creation calls return a task with a status. Creatify's lifecycle is pending, queued, running, then done, failed or rejected.
• Poll the task by id (for Aurora, GET /api/aurora/{id}/) or pass a webhook_url, per the Aurora overview. A finished Aurora task carries the file in video_output.
• AI Avatar takes aspect_ratio of 16x9, 1x1 or 9x16. If you send both text and audio, Creatify uses the audio.
• A custom avatar is reviewed before use: poll GET /api/personas/{id}/ until is_active is true.

How much does the Creatify API cost?

API access requires an active subscription. The billing page lists API Starter at $99 a month for 500 credits, API Pro at $299 a month for 2,000 credits, and API Enterprise by contact. Only creation endpoints spend credits. The per-video math for each plan, and what happens when credits run out, are in Creatify pricing and API credits.

Is there a per-second avatar and lip-sync API instead?

If you would rather pay per second of output than hold a monthly credit plan, Sume has two endpoints that cover the same two jobs. Rates are before a 5.5% agent fee by default.

• Script to avatar: POST /v1/avatar-1.0/talking-video takes a ready avatar and a script that Sume estimates at 4–60 seconds, with 720p as the documented resolution, billed at $0.184/s standard, $0.245/s plus, $0.55/s max (no product image). An optional product_image, a public HTTPS product or reference image, bills at a separate per-second rate. The avatar speaks English only in current code; see what languages an AI avatar can speak.
• Photo plus audio: VEED Fabric 1.0 (POST /v1/veed/fabric-1.0) takes a public HTTPS still or a ready avatar, plus audio of up to 300 seconds, at $0.1875 per audio second (720p). The audio must already be on Sume's media host (for example, TTS output), at most 10 MB; there is no public upload for a local file.
• Lip sync API: image and audio to a talking clip walks through the Fabric request.