The best voice ai models, according to hackers
6 voice ai models recommended in Hacker News comments over the past year, ranked by how many separate people recommend each one.
- Most recommendedGPT-Live72 people recommend it
- Least regretGemini Live50 recommend, 23 criticize
- Free and lovedNvidia PersonaPlex 7B14 people recommend it
All voice ai models
- GPT-LiveA 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'.72recommend
- Gemini LivePeople recommend it for fluent, low-latency spoken conversation across many languages, and for tutoring and practice. Critics say it sometimes loses context and misidentifies some languages.50recommend
- Nvidia PersonaPlex 7BRecommended for natural full-duplex speech conversation and a permissive license, though critics find it unintelligent and hard to keep stable without tool calling.14recommend
- gpt-realtimeRecommended for low-latency speech-to-speech and strong capabilities. Caveat: critics say it is expensive, with weaker full-duplex overlap.6recommend
- Sesame voice demoRecommended as a realtime, full-duplex voice model you can talk to on its website, with polished, natural conversation flow. One commenter found a native search tool better, but that is a single critical comment.5recommend
- UnmuteFree, open-source voice demo that lets you talk with an LLM in a more natural way. The most common caveat is that deployment is more complex than expected.5recommend