# GPT-Live Hacker Approved page: https://hackerapproved.com/p/gpt-live/ 47 people recommended GPT-Live in Hacker News comments, 21 had mixed feelings and 45 criticized it, November 2025 to October 2026. It was recommended in 4 of 12 months, in 9 threads. It does not meet the Hacker Approved badge rule. 32 of the 47 people who recommend it commented in one thread, “GPT‑Live”. **Verdict:** A real-time voice model that handles turn-taking, background noise and hands harder questions to a stronger model, praised for speed and natural voice. Critics often flag unnatural interjections like 'uh-huh'. Summary written by Claude from 51 comments. It was written before the November 2026 recount, and 50 of those comments still count. ## Why people recommend it - Delegates hard questions to a stronger model (4 comments in the sample): "I'm pretty sure that's a major part of this announcement? It delegates to GPT 5.5 which then uses tools." ([source](https://news.ycombinator.com/item?id=48835676)) "What makes this one special is that it can delegate the task to a frontier model while talking to you." ([source](https://news.ycombinator.com/item?id=48835136)) "The best feature is that it can delegate questions out to GPT-5.5 in the background" ([source](https://news.ycombinator.com/item?id=48834625)) - Useful for language practice and learning (4 comments in the sample): "If it works as well as the demo, this already crushes most language learning apps." ([source](https://news.ycombinator.com/item?id=48836806)) "This would be amazing for language listening/speaking practice." ([source](https://news.ycombinator.com/item?id=48835491)) "extremely useful at refreshing my understanding of arbitrary science concepts in playful manner" ([source](https://news.ycombinator.com/item?id=48995812)) - Better noise handling and turn-taking (3 comments in the sample): "The new architecture makes sense, it seems many of the remaining problems like noise and interruptions are at the sound processing and integration level" ([source](https://news.ycombinator.com/item?id=48835024)) "it now has much better ability to understand the conversation and decide whether it should respond" ([source](https://news.ycombinator.com/item?id=48834899)) "GPT-Live is much better at ignoring background noise, including other people speaking." ([source](https://news.ycombinator.com/item?id=48834869)) - Fast, natural voice responses (2 comments in the sample): "I've been very impressed with response speed, intonation, and naturalness to the voice." ([source](https://news.ycombinator.com/item?id=48854738)) "it's much faster, since it can reuse the background agent which now has a primed context" ([source](https://news.ycombinator.com/item?id=49657053)) ## What people warn about - Random 'hmm' and 'uh-huh' interjections (4 comments in the sample): "the interjected "uh-huh" or "yeah?" moments felt a little jarring" ([source](https://news.ycombinator.com/item?id=48834615)) "the new gpt-live feature tends to interrupt with 'human' sounding injections like "hmm", "huh" a bit too much for my liking" ([source](https://news.ycombinator.com/item?id=49006599)) "Not super impressed by the model constantly interrupting the user in the other demos" ([source](https://news.ycombinator.com/item?id=48836914)) - Voice sounds grating or cloying (3 comments in the sample): "This voice is awful, possibly one of the worst AI/computer voices I have heard in like two years now" ([source](https://news.ycombinator.com/item?id=48836308)) "Can we have less terrible voices please? Nothing that sounds like a bubbly millennial." ([source](https://news.ycombinator.com/item?id=48835765)) "I was hopeful that they avoided the well known sultry voice this go around, but alas" ([source](https://news.ycombinator.com/item?id=48835026)) - Limited empathy and reasoning (2 comments in the sample): "I am not convinced this model has enough empathy to satisfy most users on an emotional level." ([source](https://news.ycombinator.com/item?id=48835377)) "GPT-Live isn't a particularly intelligent model. It needs to handoff for reasoning and more complex tasks." ([source](https://news.ycombinator.com/item?id=48999221)) - Mishears speech and wrong-language replies (2 comments in the sample): "even seemingly GPT-Live-1 doesn't actually hear your pronunciation, it seems they all get passed transcripts" ([source](https://news.ycombinator.com/item?id=49656555)) "I tried to talk to the openai version in (my bad) korean, and it responded in japanese" ([source](https://news.ycombinator.com/item?id=49657679)) ## Other voice AI models people recommend - [Gemini Live](https://hackerapproved.com/p/gemini-3-8-live/): 40 recommend, 9 mixed, 23 criticize - [Nvidia PersonaPlex 7B](https://hackerapproved.com/p/personaplex/): 6 recommend, 5 mixed, 5 criticize - [Sesame voice demo](https://hackerapproved.com/p/sesame/): 5 recommend, 0 mixed, 1 criticize ## The badge A product earns the Hacker Approved badge when at least 10 people recommend it, recommenders outnumber critics at least 2 to 1 (mixed feelings count toward neither side), it was recommended in at least 4 of the 12 months and in at least 5 different threads, and no single thread supplies more than half of the people who recommend it. Health and money products are never badged. ## Cite as Hacker Approved, "GPT-Live", https://hackerapproved.com/p/gpt-live/ (47 recommend, 21 mixed, 45 criticize; Hacker News comments, November 2025 to October 2026). Counts updated 2 Nov 2026, with data through October 31, 2026.