Phone menu and assistant prompts
Each prompt is generated from text, so changing the menu means changing a string. For contact centres and voice apps.
- Price
- $0.125 eachwith Speech-02-Turbo
- You send
- text
- You get
- voiceover

How it works
Send text
One POST to /run with the model id and your input. It answers at once with an id.
We run Speech-02-Turbo
$0.125 each. Charged when it starts, refunded by itself if it fails.
Collect a voiceover
GET /generations/{id}?wait=55 returns an audio file of the text spoken aloud, 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": "speech-02-turbo",
"input": {
"text": "Thank you for calling. For billing, press one. For support, press two."
}
}'Full reference in the docs. Every field Speech-02-Turbo takes is on its model page.
Questions
What do I send to phone menu and assistant prompts?
Send text in one POST to https://api.percify.io/v3/playground/v1/run. You get an audio file of the text spoken aloud.
What does it cost?
With Speech-02-Turbo it is $0.125 each (5 credits each). The picks on this page range from $0.05 each 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: Qwen3 TTS Flash ($0.05 each). Balanced: Speech-02-Turbo ($0.125 each). Premium: ElevenLabs Eleven V3 ($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.
