OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time

OpenAI released GPT-Live-1 as a developer API, a full-duplex speech model that listens and talks simultaneously and is already running inside ChatGPT, priced at $0.05 per minute. On OpenAI's benchmarks, GPT-Live-1 scores 80.1 percent on full-duplex interactivity versus 45.4 percent for GPT-Realtime-2.1, cuts turn-taking latency to 0.8 seconds from 1.4 seconds, raises tool-calling accuracy to 87 percent from 60 percent, and reaches a 32 percent pass rate on a banking voice support benchmark, up from 12.4 percent. Yelp CTO Alex Levy said the company is using the model for phone-based reservations and reports better call handling, and GPT-Live-1 ships with twelve new voices plus ASR transcripts and response text out of the box.

OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time OpenAI is making GPT-Live-1 available to developers as an API. The speech model can listen and talk at the same time, a feature known as "full-duplex," https://the-decoder.com/chatgpt-can-now-listen-and-talk-at-the-same-time-making-ai-conversations-seem-more-human/ and is already running inside ChatGPT. Developers can pair it with different backend models depending on the task, matching reasoning depth, speed, and cost to each use case. At $0.05 per minute, it's not cheap. Yelp is using the model for phone-based reservations and reports better call handling, according to CTO Alex Levy https://openai.com/index/introducing-gpt-live-1-in-the-api/ . On OpenAI's benchmarks, GPT-Live-1 pulls well ahead of its predecessors. In full-duplex interactivity tests, it scores 80.1 percent compared to 45.4 percent for GPT-Realtime-2.1 https://the-decoder.com/openai-releases-new-models-for-its-realtime-api/ . Turn-taking latency drops to 0.8 seconds from 1.4 seconds. Tool-calling accuracy jumps to 87 percent from 60 percent. In a banking voice support benchmark, GPT-Live-1 hits a 32 percent pass rate, up from 12.4 percent for the previous model. GPT-Live-1 also ships with twelve new voices spanning different accents, dialects, and languages. It provides ASR transcripts and response text out of the box. Full details will be available in the API documentation https://developers.openai.com/api/docs/live . AI News Without the Hype – Curated by Humans Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section. Subscribe now OpenAI https://openai.com/index/introducing-gpt-live-1-in-the-api/