ElevenLabs ships Realtime Max/Mini speech-to-speech models with 0.57s latency
testingcatalog · x · 2026-10-21
ElevenLabs released two speech-to-speech models: Eleven Realtime v1 Max scores 98.8% on Big Bench Audio and starts speaking in 0.57s, while Eleven Realtime v1 Mini is optimized for low-cost natural conversations. Both are available on the ElevenAgents platform and via APIs for building low-latency voice agents.
Related event: ElevenLabs Launches Realtime Speech-to-Speech Models with 0.57s Latency(3 posts)→
More from Multimodal
- Painting Change Map guides fine-grained video generation of painting processes — MHUGLab · 2026-10-21
- A general VLM as a multimodal reranker: single-pass choices match dedicated rerankers — Zhuchenyang Liu · 2026-10-21
- Open-source Hermes video toolchain turns agent requests into finished MP4s — Teknium · 2026-10-21
- Argon excels as a video director, says Bindu Reddy, orchestrating SeeDance and ElevenLabs — bindureddy · 2026-10-21
- Full Midjourney prompt shared for candid morning-stretch portrait in natural window light — tisch_eins · 2026-10-21
- GameForge plugin lets Hermes Agent build playable games and playtest them itself — Teknium · 2026-10-21