ElevenLabs adds Eleven Realtime v1 Mini and Max for voice agents

ElevenLabs has added two speech-to-speech models for voice agents, Eleven Realtime v1 Mini and Eleven Realtime v1 Max. Mini is the default. Max is for long instructions and multi-step tool use. Both support 90+ languages, in ElevenAgents and on an OpenAI-compatible Realtime API. A workspace still waiting is rejected if it sets one.

The docs describe a cascaded system, not one fused model: recognition, turn-taking, a language model and a voice stay separate, and ElevenLabs does not name them. In Realtime mode it manages those parts. The agent’s prompt, voice, tools and knowledge base still apply, and Max reasons before it answers.

An app on OpenAI’s Realtime SDK can send the same events to ElevenLabs. Server-side instructions are not published yet.

The models page calls Mini the lowest-latency, lowest-cost option. The pricing page lists time to first audio as 620ms for Mini and 570ms for Max, and ElevenLabs’ post says the models start talking in half a second. Mini is not offered under Zero Retention Mode or HIPAA. Max is, in the US and the EU, but not in the India or Singapore data-residency environments, and it needs a token limit of 1,024 or no limit.

Key numbers

• Mini tokens: $0.20 per million input and $6 per million output
• Max tokens: $1.80 per million input and $9 per million output
• Connected audio: $0.08 per additional minute for both
• Included minutes vary by plan, and ElevenLabs says those minutes are estimates

ElevenLabs has not given a date for every workspace.