Skip to content
EVENT / TOPICHistorical

ElevenLabs Launches Two Real‑Time Voice Dialogue Models

1 reports1 sources10/20/2026 updated

Current overview (not historical)

AI overview

ElevenLabs has released two new real‑time speech‑to‑speech models under the Eleven Realtime brand. The v1 Max model achieved a 98.8% score on the Big Bench Audio benchmark and offers a 0.57‑second response time, positioning it for more demanding tasks such as customer‑service interactions. In contrast, the v1 Mini model focuses on natural conversational flow and cost efficiency, featuring a pause‑detection capability that identifies when a user stops speaking. These releases expand ElevenLabs’ portfolio of AI‑driven voice solutions, catering to both high‑performance and lightweight use cases.

Written with AI from the reporting · updated 10/20/2026

Latest developmentOct 21, 03:03
ElevenLabs launches two real-time speech-to-speech models for AI conversations
Explore the timeline, relations and evidence
Expand the detailed fact route and sources

Story route

A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.

  1. 1Unclassified fact stationOct 20, 00:00recorded Oct 21, 03:45single sourcerevised

    Elevenlabs releases two new speech-to-speech models

    Read original source ↗ The DecoderReplay this moment in the explorer
    Evidence & revisions · 1 source records
    Subject：
    elevenlabs
    Action：
    releases two new speech-to-speech models
    Object：
    Eleven Realtime v1 Max and v1 Mini
    Occurred (fact side)：
    Oct 20, 00:00
    The Decoder ↗Report pageRevision 2 · currently revised
    Published (valid side)：
    Oct 21, 03:03
    First seen (known side)：
    Oct 21, 03:45
    Fact stationSingle source · one-sided claimRevised

    Copy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.

Uncertainty marks flag where to check the sources; they are not proven causation.

Report timeline

Explore every side through dated source reports.

Oct 21
  1. The DecoderRelated fact: single sourceSource report revised
    ElevenLabs launches two real-time speech-to-speech models for AI conversations

    Report first recorded Oct 21, 03:45

    ElevenLabs released two new speech-to-speech models, Eleven Realtime v1 Max and v1 Mini, designed for real-time AI conversations. The v1 Max model scores 98.8 percent on the Big Bench Audio benchmark with a 0.57-second response time, positioning it as more accurate and faster than other models on the Artificial Analysis leaderboard. The smaller v1 Mini is built for natural, lower-cost conversations and can detect when a user has finished speaking. Both models are available through the ElevenAgents platform and an OpenAI-compatible Realtime API, with pricing based on per-minute costs plus token usage.

    Read original source ↗

Event discussion

Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.

Open GitHub Discussions