ElevenLabsAudio modelActive
Eleven Realtime v1 Max
Summary
Eleven Realtime v1 Max is an ElevenLabs Realtime model for voice agents. It reasons before responding and supports complex instructions and multi-step tool use. ElevenLabs says it costs more than Eleven Realtime v1 Mini, the default model of Realtime mode.
Both models rolled out gradually from October 19, 2026. The changelog reports completion for all workspaces on November 2, while the documentation still speaks of a gradual rollout. For text-only agents it points to Custom mode.
All specifications
Architecture
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
- Availability
- The changelog dates the gradual rollout from October 19, 2026, and says it completed for all workspaces on November 2. The Realtime documentation still describes the rollout as gradual.
- Source: Availability
Further details
- Behavior
- Realtime model for voice agents that reasons before responding and supports complex instructions and multi-step tool use. ElevenLabs says it costs more than Mini.
- Source: Behavior
- Intended use
- For voice agents. The documentation recommends Custom mode for text-only agents.
- Source: Intended use