Skip to main content
The Finesse API turns text into natural speech using the voices in your workspace. You add voices in the Finesse dashboard, then call the API from your own code with an API key - no SDK required. You can also clone your own voice; see Clone a voice.
1

Create voices in the dashboard

Add voices from the dashboard’s Explore library. They become available to the API once their status is ready.
You can also clone your own voice from a reference clip - in the dashboard or through /clone and /enroll.
2

Get an API key

In the dashboard, open Settings → API keys and create a key (flv_…).
3

Call the API

List your voices and synthesize speech with X-API-Key. See the Quickstart.

​
What you can do

List your voices

Discover the voices available to your API key.

Synthesize speech

Turn text into an audio file.

Stream audio

Get low-latency audio over SSE or WebSocket.

Pick the right voice

Filter by language, accent, gender, and more.

​
Start here

Quickstart

Your first API call in a few minutes.

Authentication

Create and use an API key.

API Reference

Every endpoint, with copy-paste examples.