Make your first clip
From an API key to a WAV file in a few minutes.
Clone a voice
Upload 10 seconds of one speaker and get a voice back.
Build a voice agent
Stream text in as your LLM writes it and get audio back, with barge-in.
SDKs: coming soon
Typed Python and TypeScript clients with safe retries.
Swap in for OpenAI TTS
Point code written for OpenAI’s speech endpoint at Finesse.
Browse the API
Every endpoint, with copy-paste examples.
How it works
1
Pick or clone a voice
Add voices from the dashboard’s Explore library, or clone your own from a reference clip in
the dashboard or through
/clone. A voice can speak once its status is
ready.2
Get an API key
In the dashboard, open Settings → API keys and create a
key (
flv_…). Keep it on your server. See Authentication.3
Make speech
Synthesize a clip, stream it as it is generated, or open a realtime session. The
Quickstart walks through the first call.