{"version":1,"type":"story","url":"https://digestai.news/story/elevenlabs-launches-two-realtime-speech-to-speech-models-for-ai-conver","json":"https://digestai.news/story/elevenlabs-launches-two-realtime-speech-to-speech-models-for-ai-conver.json","markdown":"https://digestai.news/story/elevenlabs-launches-two-realtime-speech-to-speech-models-for-ai-conver.md","slug":"elevenlabs-launches-two-realtime-speech-to-speech-models-for-ai-conver","headline":"Elevenlabs launches two realtime speech-to-speech models for AI conversations","summary":"Elevenlabs announced the release of two speech‑to‑speech models under the Eleven Realtime brand. The larger v1 Max variant achieved a 98.8% score on the Big Bench Audio benchmark and replies in 0.57 seconds, which the company says makes it the fastest and most accurate model on the Artificial Analysis leaderboard. The smaller v1 Mini is positioned for natural, low‑cost conversations and can detect when a speaker has finished or is only saying filler sounds like “mm‑hmm.”\n\nBoth models are reachable through the ElevenAgents platform and an OpenAI‑compatible realtime API. Pricing is charged per minute plus token usage, with v1 Max priced higher than v1 Mini. Detailed pricing information is available on Elevenlabs’ pricing page.","keyPoints":["v1 Max scores 98.8% on Big Bench Audio and responds in 0.57 seconds","v1 Mini is lower‑cost and can detect end‑of‑speech and filler “mm‑hmm”","Both models are offered via ElevenAgents and an OpenAI‑compatible realtime API with per‑minute pricing"],"whyItMatters":"Real‑time speech‑to‑speech models lower latency and cost for voice assistants, expanding practical AI conversation use cases in support and consumer apps.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Elevenlabs"],"models":["Eleven Realtime v1 Max","Eleven Realtime v1 Mini"],"people":[]},"firstPublishedAt":"2026-10-20T19:03:15Z","updatedAt":"2026-10-20T19:03:15Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"The Decoder","title":"Elevenlabs releases two new speech-to-speech models designed for real-time AI conversations","url":"https://the-decoder.com/elevenlabs-releases-two-new-speech-to-speech-models-designed-for-real-time-ai-conversations","publishedAt":"2026-10-20T19:03:15Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Elevenlabs launches two realtime speech-to-speech models for AI conversations\", 20 October 2026, https://digestai.news/story/elevenlabs-launches-two-realtime-speech-to-speech-models-for-ai-conver","publisher":"Digest AI","title":"Elevenlabs launches two realtime speech-to-speech models for AI conversations","datePublished":"2026-10-20T19:03:15Z","url":"https://digestai.news/story/elevenlabs-launches-two-realtime-speech-to-speech-models-for-ai-conver"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}