Skip to main content
This tutorial creates a voice assistant, integrating the realtime reasoning intelligence of Mercury 2 with the TTS and STT models from ElevenLabs. For this demo, you will need an Inception API key and an ElevenLabs account.
  1. Navigate to the Agents platform on the ElevenLabs sidebar.
Screenshot2026 03 02at5 07 14PM
  1. Create a Blank Agent. You can name it Mercury 2.
Screenshot2026 03 02at5 09 56PM
  1. Click into the model dropdown in the bottom right, under LLM.
Screenshot2026 03 02at5 11 18PM
  1. Scroll all the way down and select Custom LLM.
Screenshot2026 03 23at3 39 57PM
  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 Temperature to 0.75
    • Set Reasoning Effort as desired (N.B. None defaults to medium reasoning effort)
Screenshot2026 03 02at5 35 36PM
  1. Add any custom tools under the Tools tab.
Screenshot2026 03 02at5 38 06PM
  1. Amend the Mercury 2 system prompt as desired, then hit Publish in the top right corner when done!
Screenshot2026 03 02at5 39 20PM
  1. For phone integration, add Mercury 2 as the assigned agent to pick up your phone calls.
Screenshot2026 03 02at5 39 55PM