Percify APIUpdate a product demo without reshooting
An existing demo video gets new lines with the presenter's lips matching, so a feature change needs no new shoot. For product teams with recorded demos.
How it works
Send the new lines as text
Text to speech turns it into an audio file of the new lines. That goes with the video you already have in the second call.
We run InfiniteTalk Fast
$0.032 a second, plus $0.12 a 1,000 characters for step 1. Charged when it starts, refunded by itself if it fails.
Collect a revoiced video
GET /generations/{id}?wait=55 returns the same video with the speaker saying your new lines, lips in sync, as a file URL. Or pass a webhook and we call you.
Make the new lines as audio first (use voice cloning instead to keep the original voice), then send that audio with the video.
2 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
Step 2, with a sample file where the audio from step 1 goes. 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": "speech-02-turbo",
"input": {
"text": "The new version also syncs with your calendar, so meetings appear automatically."
}
}'curl https://api.percify.io/v3/playground/v1/run \
-H "Authorization: Bearer $PERCIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"modelId": "infinitetalk-fast",
"input": {
"audio": "https://cdn.percify.io/media-assets/playground/e320274d-865f-4ea9-ad76-70fcd5d025df-0",
"image": "https://cdn.percify.io/media-assets/playground-examples/infinitetalk-fast/4.mp4",
"prompt": "The new version also syncs with your calendar, so meetings appear automatically."
}
}'Full reference in the docs. Every field InfiniteTalk Fast takes is on its model page.
Questions
What do I send to update a product demo without reshooting?
Two calls. First the new lines as text, which returns an audio file of the new lines. Then the video you already have and the audio from step 1 in one POST to https://api.percify.io/v3/playground/v1/run. You get the same video with the speaker saying your new lines, lips in sync.
What does it cost?
With InfiniteTalk Fast it is $0.032 a second (1.6 credits a second at the lowest setting; higher resolutions and audio cost more). The picks on this page range from $0.032 a second to $0.06 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: InfiniteTalk Fast ($0.032 a second). Premium: InfiniteTalk ($0.06 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
Rewrite what people say in a videoThe clip keeps its scene and performance while the speaker says your new lines, with the lips matched to them.
Fix one line in a finished adA wrong price or claim in a finished ad is replaced with the right line, lips in sync, without a reshoot.
Make a photo talkOne photo and one audio file become a video of that person speaking, with the lips in sync.
