Vapi

This tutorial creates a voice agent, integrating the realtime reasoning intelligence of Mercury 2 with Vapi. For this demo, you will need an Inception API key and a Vapi account.

​

Authentication

1. Navigate to Integrations in the Vapi sidebar.

2. Under Model Providers, click into Custom LLM (bottom right).

3. Fill in your Inception API key and click Save.

​

Setting up your Mercury voice agent

1. Navigate to Agents in the Vapi sidebar and select Create Assistant.

2. Name your assistant and select your desired assistant template.

3. Select Custom llm from the Model dropdown:

4. Fill in model details as follows:
   • Set Custom LLM URL as https://api.inceptionlabs.ai/v1
   • Set Model as mercury-2
   • Set Temperature to 0.75
   • Set Max Tokens to a slightly higher value, like 4096. This is because the default reasoning effort is medium, and Max Tokens includes reasoning tokens.
   • Configure First Message Mode, First Message and System Prompt as desired.
     • Scroll down to manage Tools, Structured Outputs and more.

5. When you’re ready, hit Publish in the top right corner, and Talk to speak to Mercury 2!