One-click effects and full Compose recipes for AI video. Pick an effect, open a production recipe, or pass the right slug to the API.
Every effect below opens in the playground template browser. Featured effects come first.
Compose turns a topic, script, or product idea into a planned, voiced, captioned short-form video. The cards below come from the same live recipe catalog used by the playground and API.
Templates work on the generation endpoints by adding a single template field to the request body:
curl https://api.empiriolabs.ai/v1/videos/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling-o3",
"template": "<template-slug>",
"prompt": "Describe your subject."
}'Compose is a full production workflow. List recipes, plan the storyboard, then render the final video:
curl https://api.empiriolabs.ai/v1/videos/compose \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"recipe": "custom",
"mode": "plan",
"brief": "Explain why cold plunge clips went viral.",
"aspect_ratio": "9:16",
"scene_count": 5
}'Compose currently exposes 20 caption styles and 8 custom visual style presets from the live catalog, so playground output and API output stay aligned.
Curated recipes for trending AI video and image effects. Each template carries a tuned setup for a specific look or format, so one click (or one API field) produces the effect without prompt engineering.
Compose recipes are full-production workflows. They plan scenes, create or select visuals, add voiceover, captions, optional music, and return a finished short-form video.
Yes. Pass "template": "<slug>" on POST /v1/videos/generations or POST /v1/images/generations along with your prompt, and the template is applied to the request.
Yes. Use GET /v1/videos/compose/recipes to list public recipe metadata, then call POST /v1/videos/compose with mode: "plan" or mode: "render".
Every template has a recommended model it was tuned on, and many support several models. The playground preselects the recommended model when you pick a template; on the API you choose the model id yourself.
Open the template browser in the playground, pick a template, and generate. Billing is the normal pay-as-you-go rate of the model you run.
Check out our pricing or reach out if you want your own model deployed on our stack.