Rime launches prism speech-to-speech model: 300ms response, 4x faster than OpenAI
EXM7777 · x · 2026-10-29
Rime, a 35-person team with $35M in funding, launched prism — billed as the first speech-to-speech model indistinguishable from a human in conversation. It claims a 300ms response time (4x faster than OpenAI GPT-Live), top intelligence scores among s2s models without reasoning, RL-based customization, natural imperfections like laughter and filler words, mid-conversation language switching, and sub-100ms latency for real-time calls. Rime says it has already powered over a billion calls — a direct challenge to ElevenLabs and the demo-only era of AI voice.
Related event: Rime Unveils Prism Speech-to-Speech Model with 300ms Response(2 posts)→
More from Models
- OpenAI Dot proactively catches user's meeting date mix-up by monitoring email — kimmonismus · 2026-10-29
- MiniMax M3.1 Flash accused of benchmaxxing after -22 point drop on updated AA Omniscience Index — rickasaurus · 2026-10-29
- GPT-6.1 Sol capacity limits stall overnight agent tasks after 45 minutes — CtrlAltDwayne · 2026-10-29
- Rumor: Anthropic reportedly has internal model beating Mythos 5.1 with better alignment — VraserX · 2026-10-29
- DIAL Benchmark Ranks Speech-to-Speech Models With 30k+ Human Ratings Across 9k Live Calls — sarahcat21 · 2026-10-29
- Benchmaxxing debate: is training on test despicable or the vertical AI superpower? — HanchungLee · 2026-10-29