Build your first brain
Go from an empty file to a talking agent in a few minutes. Quickstart →
Voqalize
A voice operator that lives inside your app. You write the brain; Voqalize runs the voice.
Voqalize runs the voice stack — WebRTC, voice activity detection, speech-to-text, text-to-speech, interruption handling, recording. You write the brain: an agent that receives text and speaks text back. Your code never touches audio.
Start here
Section titled “Start here”Understand the model
One WebSocket per session, the Vql* frame set, and where the brain runs.
Core concepts →
Pick your language
A brain is a short subclass. Build it in Python.
Put a voice in the browser
Embed a live agent in a web app with the React client SDK.
What is a Voqalize app?
Section titled “What is a Voqalize app?”A brain is a single WebSocket URL. Voqalize dials {brain_url}/s/{session_id},
one connection per session, opened when a call starts and torn down when it ends.
Where that URL points is up to you — your own inbound server, or a Cortex relay
for brains that can’t accept inbound connections. Same brain code either way;
you only choose who dials whom. See Where the brain runs.