The Pulse
ElevenLabs Launches Realtime Speech-to-Speech Models for Voice Agents
ElevenLabs launched Eleven Realtime v1 Mini and v1 Max for building voice agents, with support for more than 90 languages and 17,000-plus voices. Max scored 98.8% on a speech-reasoning benchmark, the company says, while both models are available through ElevenAgents and a WebSocket API.

ElevenLabs launched two speech-to-speech models on October 20, 2026, aimed at developers building voice agents. Eleven Realtime combines speech recognition, turn-taking, a language model and voice output in a single agent choice, instead of asking builders to configure each component separately. Min Kim, the author of ElevenLabs’ announcement, writes: “Each model is a complete voice agent, optimized for separate use cases.”
Mini and Max target different conversations
Eleven Realtime v1 Mini is designed for lower-cost, natural exchanges such as AI assistants, tutors and interactive characters. The v1 Max model is aimed at customer support, lead qualification and other workflows where an agent must follow steps, use tools or reason through a more complex request. Both models support more than 90 languages and can use voices from ElevenLabs’ library of more than 17,000 voices, according to the company.
The model choice changes how the agent’s components are managed, but does not remove every configuration option. Prompts, voices, tools, knowledge bases and conversation-flow settings remain available in Realtime mode. Realtime models are for voice agents created in ElevenAgents; agents built through other ElevenLabs products, including Speech Engine, cannot use them.
Benchmark results favor Max on reasoning and tools
Artificial Analysis independently evaluated the models on three public benchmarks, according to ElevenLabs. In Big Bench Audio, which asks 1,000 spoken reasoning questions and scores the answers, Max answered 98.8% correctly and Mini answered 75.9%. Average time to first audio was 0.57 seconds for Max and 0.62 seconds for Mini, the company reports.
The results are not uniformly higher for Max. On Full-Duplex-Bench, which tests pauses, turn-taking, interruptions and backchannels, Mini scored 95.8% and Max 94.1%. Speech Agent Arena scores were 998 for Max and 988 for Mini, and tool-use task completion rates 87.1% and 60.3%, respectively, ElevenLabs reports. Those figures come from the company’s launch post; they describe different evaluations and should not be read as a single overall score.
OpenAI-compatible API comes with a transport limit
Developers can select a Realtime model inside ElevenAgents or connect through ElevenLabs’ Realtime API. The API follows OpenAI’s Realtime specifications, allowing developers with an existing compatible integration to change the endpoint and model name rather than rebuild the client. The connection uses WebSocket, however, so an integration built for WebRTC must move to WebSocket to use this API.
The Realtime API also runs separately from ElevenAgents. Developers who need ElevenAgents features such as phone and WhatsApp channels, workflows, a knowledge base, guardrails or monitoring must use that platform rather than the standalone API, according to the announcement.
Pricing and rollout are not identical for both models
Realtime agents carry the standard ElevenAgents per-minute charge plus input, cached-input and output token charges at the model’s rates; Max costs more per token than Mini. The launch post does not provide specific prices. Availability is a gradual rollout, so the Realtime option may not yet appear in every workspace.
That leaves developers weighing two practical constraints alongside the benchmark results: whether Realtime has reached their workspace and whether their existing audio client uses WebSocket. Mini is the lower-cost, lower-latency choice in ElevenLabs’ product guidance; Max is the more expensive option for complex instructions and multi-step tool use.
Sources
- Original source · Blog post ElevenLabs elevenlabs.io
Other pages read
- ElevenLabs Documentation · Realtime models elevenlabs.io
- ElevenLabs Documentation · Openai realtime compatibility elevenlabs.io