Percify APIGive a podcast clip a face
An audio clip and a host photo become a talking video for Shorts, Reels and TikTok. For podcasters posting clips to video platforms.
- Price
- $0.05 a secondwith InfiniteTalk Fast
- You send
- a photo of a face and an audio file
- You get
- talking video
How it works
Send a photo of a face and an audio file
One POST to /run with the model id and your input. It answers at once with an id.
We run InfiniteTalk Fast
$0.05 a second. Charged when it starts, refunded by itself if it fails.
Collect a talking video
GET /generations/{id}?wait=55 returns a video of that face speaking the audio, lips in sync, as a file URL. Or pass a webhook and we call you.
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
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": "infinitetalk-fast",
"input": {
"audio": "https://cdn.percify.io/media-assets/playground/e320274d-865f-4ea9-ad76-70fcd5d025df-0",
"image": "https://cdn.percify.io/media-assets/web-v3/products/uc-founder.jpg"
}
}'Full reference in the docs. Every field InfiniteTalk Fast takes is on its model page.
Questions
What do I send to give a podcast clip a face?
Send a photo of a face and an audio file in one POST to https://api.percify.io/v3/playground/v1/run. You get a video of that face speaking the audio, lips in sync.
What does it cost?
With InfiniteTalk Fast it is $0.05 a second (2 credits a second). The picks on this page range from $0.05 a second to $0.10 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 ($0.05 a second). Premium: InfiniteTalk ($0.10 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.
- Turn a voice message into a video greetingA recorded message and a photo become a video greeting someone can share.
- Narration for articles and booksLong text becomes narration, a chapter at a time.
