{"slug": "openai-s-gpt-live-1-api-lets-developers-build-apps-that-talk-and-listen-at-the", "title": "OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time", "summary": "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.", "body_md": "# OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same time\n\n**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/).\n\nOn 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.\n\nGPT-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).\n\n```\nAI News Without the Hype – Curated by Humans\n\n\t\t\t\t\tSubscribe 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.\t\t\t\t\n\n\t\t\t\t\tSubscribe now\n```\n\n[OpenAI](https://openai.com/index/introducing-gpt-live-1-in-the-api/)", "url": "https://wpnews.pro/news/openai-s-gpt-live-1-api-lets-developers-build-apps-that-talk-and-listen-at-the", "canonical_source": "https://the-decoder.com/openais-gpt-live-1-api-lets-developers-build-apps-that-talk-and-listen-at-the-same-time/", "published_at": "2026-09-10 17:47:35+00:00", "updated_at": "2026-09-10 18:07:57.671593+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-products", "ai-tools", "natural-language-processing", "developer-tools"], "entities": ["OpenAI", "GPT-Live-1", "ChatGPT", "GPT-Realtime-2.1", "Yelp", "Alex Levy"], "alternates": {"html": "https://wpnews.pro/news/openai-s-gpt-live-1-api-lets-developers-build-apps-that-talk-and-listen-at-the", "markdown": "https://wpnews.pro/news/openai-s-gpt-live-1-api-lets-developers-build-apps-that-talk-and-listen-at-the.md", "text": "https://wpnews.pro/news/openai-s-gpt-live-1-api-lets-developers-build-apps-that-talk-and-listen-at-the.txt", "jsonld": "https://wpnews.pro/news/openai-s-gpt-live-1-api-lets-developers-build-apps-that-talk-and-listen-at-the.jsonld"}}