{"slug": "gpt-live-1", "name": "GPT-Live-1", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 5, "warners": 0, "score": 3.491, "rising": 3.0, "first": "2026-09-11", "latest": "2026-09-16", "why": "you'll realize this is obviously the future interface.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 2, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "you'll realize this is obviously the future interface.", "icon": false, "domain": null, "github_repo": null, "official_url": "", "pricing": "", "aliases": ["GPT-Live-1"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 795698432, "item_id": 49731152, "url": "https://news.ycombinator.com/item?id=49731152", "by": "SyneRyder", "date": "2026-09-16", "stance": "recommend", "quote": "you'll realize this is obviously the future interface.", "excerpt": "So, the way GPT-Live-1 works, the Live model just handles the conversation layer in a lightweight manner. For any deeper thinking (and I think tool calls) it will delegate to the Backend. It's like how Fable can delegate tasks to Opus while it keeps going. The Live voice can keep chatting to you while it waits for results from the Backend. The default for the Backend is a Responses Delegation that just sends it to an", "context": "built voice harness in Go", "use_case": "voice interface with Claude backend", "switched_from": "", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 794512848, "item_id": 49657053, "url": "https://news.ycombinator.com/item?id=49657053", "by": "dist-epoch", "date": "2026-09-11", "stance": "recommend", "quote": "once you get it going, it's much faster, since it can reuse the background agent which now has a primed context.", "excerpt": "I used it in a similar way, and once you get it going, it's much faster, since it can reuse the background agent which now has a primed context. I got 30 sec turn around times. And you can talk about the next change while the previous one is being implemented.", "context": "", "use_case": "voice-driven coding changes", "switched_from": "", "story": "GPT\u2011Live\u20111 in the API"}, {"id": 794495744, "item_id": 49655984, "url": "https://news.ycombinator.com/item?id=49655984", "by": "thiago_fm", "date": "2026-09-11", "stance": "recommend", "quote": "I really love their product. It's the fucking best, a life changer.", "excerpt": "Damn, this was a terrible showcase of their voice API, I really love their product. It's the fucking best, a life changer. But... what a meh showcase. Is somebody from OpenAI hiring? I can show how I use it to learn German, among other very interesting usages. Also show proper excitement etc... I think also a lot of real users could do better. It feels like they aren't real users of their own products...", "context": "", "use_case": "learning German", "switched_from": "", "story": "GPT\u2011Live\u20111 in the API"}]}], "caveats": [], "who": [{"by": "SyneRyder", "context": "built voice harness in Go", "url": "https://news.ycombinator.com/item?id=49731152", "date": "2026-09-16"}, {"by": "adityashankar", "context": "learning German", "url": "https://news.ycombinator.com/item?id=49655961", "date": "2026-09-11"}], "tags": [], "use_cases": ["voice interface with claude backend", "voice-driven coding changes", "voice assistant realtime", "learning german", "conversational language practice"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49653985", "title": "GPT\u2011Live\u20111 in the API", "mentions": 4}, {"url": "https://news.ycombinator.com/item?id=49715947", "title": "Gemini 3.8 Live and 3.8 Live Extended Thinking", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {}, "2026-09": {"neutral": 2, "recommend": 3}, "2026-10": {}}, "quotes": [{"id": 795698432, "item_id": 49731152, "url": "https://news.ycombinator.com/item?id=49731152", "by": "SyneRyder", "date": "2026-09-16", "stance": "recommend", "quote": "you'll realize this is obviously the future interface.", "excerpt": "So, the way GPT-Live-1 works, the Live model just handles the conversation layer in a lightweight manner. For any deeper thinking (and I think tool calls) it will delegate to the Backend. It's like how Fable can delegate tasks to Opus while it keeps going. The Live voice can keep chatting to you while it waits for results from the Backend. The default for the Backend is a Responses Delegation that just sends it to an", "context": "built voice harness in Go", "use_case": "voice interface with Claude backend", "switched_from": "", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 794512848, "item_id": 49657053, "url": "https://news.ycombinator.com/item?id=49657053", "by": "dist-epoch", "date": "2026-09-11", "stance": "recommend", "quote": "once you get it going, it's much faster, since it can reuse the background agent which now has a primed context.", "excerpt": "I used it in a similar way, and once you get it going, it's much faster, since it can reuse the background agent which now has a primed context. I got 30 sec turn around times. And you can talk about the next change while the previous one is being implemented.", "context": "", "use_case": "voice-driven coding changes", "switched_from": "", "story": "GPT\u2011Live\u20111 in the API"}, {"id": 794501712, "item_id": 49656357, "url": "https://news.ycombinator.com/item?id=49656357", "by": "ndom91", "date": "2026-09-11", "stance": "neutral", "quote": "Been wanting to try this out on top of https://github.com/TristanBrotherton/voicepe-realtime with the HomeAssistant VoicePE", "excerpt": "Been wanting to try this out on top of https://github.com/TristanBrotherton/voicepe-realtime with the HomeAssistant VoicePE Anyone else hack something together with HA / the Voice PE yet? Looks like it needs a second model to do function calling, which gpt-realtime-2.5 didn't, and the Voice PE XMOS chip's audio pipeline might not be a great fit for full duplex back and forth, like what gpt-live-1 now supports.", "context": "", "use_case": "voice assistant realtime", "switched_from": "", "story": "GPT\u2011Live\u20111 in the API"}, {"id": 794495744, "item_id": 49655984, "url": "https://news.ycombinator.com/item?id=49655984", "by": "thiago_fm", "date": "2026-09-11", "stance": "recommend", "quote": "I really love their product. It's the fucking best, a life changer.", "excerpt": "Damn, this was a terrible showcase of their voice API, I really love their product. It's the fucking best, a life changer. But... what a meh showcase. Is somebody from OpenAI hiring? I can show how I use it to learn German, among other very interesting usages. Also show proper excitement etc... I think also a lot of real users could do better. It feels like they aren't real users of their own products...", "context": "", "use_case": "learning German", "switched_from": "", "story": "GPT\u2011Live\u20111 in the API"}, {"id": 794495376, "item_id": 49655961, "url": "https://news.ycombinator.com/item?id=49655961", "by": "adityashankar", "date": "2026-09-11", "stance": "neutral", "quote": "I gotta retry with GPT-live-1", "excerpt": "Oh yeah, I built so much stuff to learn German, for example [1] to give me random German texts, force me to read it, and answer it, I created [2] to automatically make flashcards for me and then use with with a flashcards app I regularly use and [3] to help me memorise German cases and word-genders. I love it! I did think of implementing this conversationally, but tbh it has always been too expensive thus far, I gott", "context": "learning German", "use_case": "conversational language practice", "switched_from": "", "story": "GPT\u2011Live\u20111 in the API"}]}