{"schema":"postcutoff/event@1","as_of":"2026-10-25T23:49:00+01:00","url":"https://postcutoff.com/e/2026-10-20-eleven-realtime-speech-to-speech/","md":"https://postcutoff.com/e/2026-10-20-eleven-realtime-speech-to-speech/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-20-eleven-realtime-speech-to-speech","date":"2026-10-20","date_precision":"day","short_title":"ElevenLabs Eleven Realtime","deck":null,"takeaway":"On Oct 20, 2026 ElevenLabs released two speech-to-speech models for voice agents: v1 Max for multi-step, tool-heavy work and v1 Mini for cheap conversation, both in 90+ languages with any of 17,000+ voices.","category":"product","category_label":"Products","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"ElevenLabs: Eleven Realtime (Oct 20)","url":"https://elevenlabs.io/blog/realtime","type":"official","group":"primary","domain":"elevenlabs.io"},{"n":2,"title":"ElevenLabs docs: OpenAI Realtime compatibility","url":"https://elevenlabs.io/docs/eleven-agents/guides/openai-realtime-compatibility","type":"docs","group":"primary","domain":"elevenlabs.io"}],"official":2,"filed":"2026-10-25","updated":"2026-10-25","orgs":["ElevenLabs"],"title":"ElevenLabs launches Eleven Realtime v1 Max and Mini, speech-to-speech voice-agent models compatible with OpenAI's Realtime API","summary":"On Oct 20, 2026 ElevenLabs released two speech-to-speech models for voice agents: v1 Max for multi-step, tool-heavy work and v1 Mini for cheap conversation, both in 90+ languages with any of 17,000+ voices. The API mirrors OpenAI's Realtime API, so switching is mostly a change of endpoint and model name. Artificial Analysis measured Max at 98.8% on Big Bench Audio and 87.1% on tool use.","key_facts":["Published Oct 20, 2026; two models: Eleven Realtime v1 Max (complex support and lead-qualification flows, heavy tool calling) and v1 Mini (assistants, tutors, characters)","Artificial Analysis figures quoted by ElevenLabs: Big Bench Audio Max 98.8% / Mini 75.9%; Full-Duplex-Bench Mini 95.8% / Max 94.1%; Speech Agent Arena Max 998 / Mini 988; tool use Max 87.1% / Mini 60.3%; time to first audio ~0.57 s (Max), ~0.62 s (Mini)","OpenAI Realtime API compatible over WebSocket (not WebRTC); OpenAI's SDK works unchanged; runs separately from the ElevenAgents platform","AA speech-to-speech index (read 2026-10-25): v1 Max #6 of 21 (77.3)"],"key_numbers":[],"tags":["speech-to-speech","voice-agents","realtime","audio","api"],"science":null,"body_md":"## What happened\n\nElevenLabs, until now mostly a text-to-speech company, shipped end-to-end speech-to-speech models for voice agents and made them a\ndrop-in replacement for OpenAI's Realtime API.\n\n## Why it matters\n\nVoice agents are shifting from speech-to-text, LLM and text-to-speech pipelines to single speech models; ElevenLabs is competing\ndirectly with OpenAI on that layer.","disputed":[],"related":[{"id":"2026-10-23-block-dessa-speech-only-full-duplex-model","url":"https://postcutoff.com/e/2026-10-23-block-dessa-speech-only-full-duplex-model/","date":"2026-10-23","date_precision":"day","short_title":"Block unveils Dessa, a full-duplex voice model trained from scratch only on recorded human conversation, with no text and no pretrained model","deck":null,"takeaway":"Most voice assistants of 2026 convert speech to text or are built on text-trained models.","category":"research","category_label":"Research","importance":3,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":4,"official":2,"filed":"2026-10-24","updated":"2026-10-24","orgs":["Block"]}],"people":[],"posts":[],"videos":[],"models":[{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","url":"https://postcutoff.com/m/eleven-realtime-v1-max/"}],"changes":[{"date":"2026-10-25","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-25","run":null,"sources_read":null,"updated":"2026-10-25","human_review":null,"version":{"date":"2026-10-25"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":173,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":112,"in_training_data":false},{"model_id":"gemini-4-argon","name":"Gemini 4 Argon","cutoff":"2026-03","days_after":203,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":142,"in_training_data":false}],"short_url":null}