Percify APIYour own voice on every video
A creator records a sample once and every later script is spoken in their voice. For creators who publish daily.
- Price
- from $0.05with Zonos 2
- You send
- a short voice sample and the text to speak
- You get
- cloned voice clip
How it works
Send a short voice sample and the text to speak
One POST to /run with the model id and your input. It answers at once with an id.
We run Zonos 2
from $0.05. Charged when it starts, refunded by itself if it fails.
Collect a cloned voice clip
GET /generations/{id}?wait=55 returns the text spoken in the sampled voice, 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": "zonos2",
"input": {
"text": "Welcome back to the channel. Today we are testing something new.",
"audio": "https://cdn.percify.io/media-assets/playground/e320274d-865f-4ea9-ad76-70fcd5d025df-0"
}
}'Full reference in the docs. Every field Zonos 2 takes is on its model page.
Questions
What do I send to your own voice on every video?
Send a short voice sample and the text to speak in one POST to https://api.percify.io/v3/playground/v1/run. You get the text spoken in the sampled voice.
What does it cost?
With Zonos 2 it is from $0.05 (from 2 credits). The picks on this page range from from $0.05 to $0.25 each. 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: Zonos 2 (from $0.05). Premium: XTTS-v2 ($0.25 each). 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
- Clone a voice from a short sampleA short sample and a line of text return that line in the sampled voice.
- A news presenter from headlinesA daily text briefing becomes a presenter video without a studio.
- B roll on demandA described shot becomes a clip to drop into the timeline when stock footage has nothing.
