Skip to main content
This tutorial creates a voice assistant, integrating the realtime reasoning intelligence of Mercury 2.5 with the TTS and STT models from ElevenLabs. For this demo, you will need an Inception API key and an ElevenLabs account.
Prefer to build the voice loop yourself in code? See the Realtime Voice Assistant cookbook.
  1. Navigate to the Agents platform on the ElevenLabs sidebar.
ElevenLabs sidebar with the Agents platform selected
  1. Create a Blank Agent. You can name it Mercury 2.5.
Creating a blank agent in ElevenLabs
  1. Click into the model dropdown in the bottom right, under LLM.
Opening the LLM model dropdown in the ElevenLabs agent settings
  1. Scroll all the way down and select Custom LLM.
Selecting Custom LLM in the ElevenLabs model list
  1. Fill in Custom LLM details as follows:
    • Add your Inception API key by clicking API Key —> Create new secret
    • Set Server URL to https://api.inceptionlabs.ai/v1
    • Set Model ID to mercury-2.5
    • Set Temperature to 0.75
    • Set Reasoning Effort as desired (N.B. leaving it unset defaults to medium reasoning effort)
  2. Add any custom tools under the Tools tab.
Adding custom tools under the Tools tab in ElevenLabs
  1. Amend the Mercury 2.5 system prompt as desired, then hit Publish in the top right corner when done!
  2. For phone integration, add Mercury 2.5 as the assigned agent to pick up your phone calls.