How can we help?
Find answers, explore guides, or contact our support team.
Getting Started
12 articles
Billing & Credits
8 articles
API & Integration
15 articles
Account & Security
6 articles
Commerce workflow quick answers
Direct links Sales can send for image enhancement, background replacement, short motion from stills, narrated commerce clips, and webhook-backed delivery.
Automation, demo & platform quick answers
Paste-ready proof for Clueso, Supademo, Creatomate, Plainly, RenderForm, Bannerbear, JSON2Video, and similar async workflow buyers.
Can CreativeAI sit behind our existing media API as partner or overflow capacity?How are generated assets delivered, and do we need our own storage layer?Can CreativeAI plug into automation or demo platforms without extra rendering infrastructure?What if our workflow platform cannot receive inbound webhooks?How should automation buyers think about capacity and concurrency?Can one API handle screenshots, short clips, and voiceovers for demos or product education?
Buyer-safe proof pack
One compact link Sales can share for commerce, API-platform, and audio/multilingual workflow proof.
Commerce visuals
- Image enhancement — sharpen, relight, and upscale product photos via the images/edits endpoint (3–5 credits).
- Background replacement — describe a new scene; the model preserves the subject and composites automatically. No manual masking.
- Short motion from stills — submit a product image to video/generations for a 5–10 s turntable or lifestyle clip. Async with webhook or polling delivery.
- Narrated commerce clips — pair voice generation with /api/generate/compose to turn a cleaned-up product still into a voiced MP4 without adding a second media vendor.
API & platform integration
- Overflow / partner capacity — call CreativeAI behind your own API for extra still, video, or voice capacity without re-architecting your workflow.
- Storage posture — completed assets are CDN-delivered by default; download into your own bucket on your own schedule for tighter retention control.
- Standard async wording — Webhook delivery uses 3 attempts with exponential backoff (0s, 5s, 30s). If delivery still fails, the final result remains available via the status API.
Audio & multilingual
- Text-to-speech — 6 voices, 10 languages, adjustable speed. Generate via Audio Studio or the voice API.
- Documentation & demo workflows — one API key covers stills, short video, and multilingual voiceover clips so teams skip multi-vendor stitching.
- Same async model — voice generation uses the same submit → poll/webhook pattern as video, keeping integration uniform.
Frequently Asked Questions
Credits are our universal currency for AI generation. Different operations cost different amounts: images typically cost 3 credits, videos 25 credits, and voice synthesis 5-10 credits depending on length.