Voice and music · by OpenAI

GPT-Live

Have phone calls with a voice that listens while it talks.

speech, text → speech, text, events · text → profile · speech, text → sent, speech
Way in
Official APISign up yourself, api key
To start
$none
Runs
In the cloud
Checked
Nov 3, 2026Prices as of that day

What it can do 3

Run a full-duplex spoken conversation that hands tasks to a backend model or your own agentconcurrent sessions: 50 (Build), 300 (Launch), 500 (Grow); free tier unsupported; no image/video inputspeech, text → speech, text, events$0.05/min, billed per second + backend model/tool usage
Create a reusable custom voice from a text description (prompt-to-voice)reported limit 100 voices per org (secondary)text → profilefree to create; speech billed at GPT-Live rates
Answer or place phone calls over SIPspeech, text → sent, speech$0.05/min + carrier

Does the same job

Prices and limits as of Nov 3, 2026, from OpenAI’s own pages. They change; check before you rely on them.Not affiliated with OpenAI. Not advice.Something wrong?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.