Percify APIEdit a video with a prompt
A video and an instruction return the video with that change. For video editing tools.
- Price
- $0.25 a secondwith Lucy Edit Pro (Video Edit)
- You send
- a video and the change you want in words
- You get
- edited video
How it works
Send a video and the change you want in words
One POST to /run with the model id and your input. It answers at once with an id.
We run Lucy Edit Pro (Video Edit)
$0.25 a second. Charged when it starts, refunded by itself if it fails.
Collect an edited video
GET /generations/{id}?wait=55 returns the video with the change applied, as a file URL. Or pass a webhook and we call you.
3 models for this, by price
Prices are read from the live catalog. Each one opens the playground with this use case filled in.
The request
Filled in with sample files from our CDN, so it runs as it is. Swap in your own URLs.
curl https://api.percify.io/v3/playground/v1/run \
-H "Authorization: Bearer $PERCIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"modelId": "lucy-edit-pro",
"input": {
"video": "https://cdn.percify.io/media-assets/playground-examples/infinitetalk-fast/4.mp4",
"prompt": "Change the background to a bright modern office"
}
}'Full reference in the docs. Every field Lucy Edit Pro (Video Edit) takes is on its model page.
Questions
What do I send to edit a video with a prompt?
Send a video and the change you want in words in one POST to https://api.percify.io/v3/playground/v1/run. You get the video with the change applied.
What does it cost?
With Lucy Edit Pro (Video Edit) it is $0.25 a second (10 credits a second). The picks on this page range from $0.15 a second to $3.50 a second. The estimate call returns the exact price of your input before you run it, and a run that fails is refunded.
Which model should I use?
Budget: Grok Imagine Video Edit ($0.15 a second). Balanced: Lucy Edit Pro (Video Edit) ($0.25 a second). Premium: Wan 2.7 Video Edit ($3.50 a second). Switching is one string in the request: the model id.
Can an AI agent do this for me?
Yes. Connect your agent to the MCP server at https://mcp.percify.io/mcp and ask for it in plain words. The agent calls the generate tool with the same model id and input shown on this page, and the call spends the same credits.
Related use cases
- Make a photo talkOne photo and one audio file become a video of that person speaking, with the lips in sync.
- Video replies for an AI characterA chat reply becomes a short video of the character saying it.
- Generate video from a text promptA sentence becomes a video clip, with the model chosen by one string in the request.
