ElevenLabsAudio modelActive
Eleven Realtime v1 Mini
Summary
Eleven Realtime v1 Mini is the default model in the Realtime mode of ElevenLabs voice agents. ElevenLabs describes it as the Realtime model with the lowest latency and cost. For more complex instructions there is Eleven Realtime v1 Max.
The gradual rollout began on October 19, 2026; according to the changelog it completed for all workspaces on November 2, while the Realtime documentation still describes it as gradual. The model is meant for voice agents; for text-only agents the documentation recommends 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
- Default Realtime model for voice agents. ElevenLabs describes Mini as the Realtime model with the lowest latency and cost.
- Source: Behavior
- Intended use
- For voice agents. The documentation recommends Custom mode for text-only agents.
- Source: Intended use