Sakhanda Wire
NVDA $153.73 -1.54% MSFT $506.30 -2.26% GOOGL $280.09 -1.28% META $619.28 -1.14% AMZN $256.62 -0.44%
← Back to the news

OpenAI offers GPT-Live-1 speech model through developer API

OpenAI has made GPT-Live-1 available to developers through an API. The speech model supports full-duplex interaction, allowing it to listen and speak at the same time. It is already used inside ChatGPT, while developers can connect it to different backend models according to the required balance of reasoning capability, speed, and cost. The API is priced at $0.05 per minute.

Yelp is using GPT-Live-1 for telephone reservations. Its CTO, Alex Levy, said the company has seen improved call handling. OpenAI’s tests give the model an 80.1 percent score for full-duplex interactivity, compared with 45.4 percent for GPT-Realtime-2.1. Turn-taking latency was measured at 0.8 seconds, versus 1.4 seconds for the earlier model, while tool-calling accuracy rose to 87 percent from 60 percent.

In a banking voice-support benchmark, GPT-Live-1 achieved a 32 percent pass rate, up from 12.4 percent for its predecessor. The release also includes twelve voices covering different accents, dialects, and languages, along with ASR transcripts and response text.

Written by Sakhanda Wire AI from reporting by The Decoder. Facts, quotes and full context are in the original article below.

Originally published by The Decoder on

Read the original on The Decoder ↗

The reporting and the image belong to The Decoder and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news