> ## Documentation Index
> Fetch the complete documentation index at: https://docs.inceptionlabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Vapi
> Build a low-latency voice agent in Vapi using Mercury 2.
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](https://platform.inceptionlabs.ai/dashboard/api-keys) and a [Vapi account](https://www.google.com/aclk?sa=L\&pf=1\&ai=DChsSEwjLwOWh7M-TAxXAKa0GHT5lPZAYACICCAEQABoCcHY\&co=1\&ase=2\&gclid=Cj0KCQjwp7jOBhDGARIsABe7C4f-qDhHW788QcWCYBd583bC4Gpo4laM0LLv_BsBjRE2BD-_5ygoip0aAjfJEALw_wcB\&ei=AbzOaciABqOh0PEP9p2F6Ac\&cid=CAASWuRoXJCWLNPBZD6y4USgryROi0niu0LFXfnNnM13W9Mpb_4GdglqL11d0RpiY7rfiN6gSOZo4I9bDozBnvktudqJEdX6GfL1K-K8-p5wNkaPwenLuXzJG_5icg\&cce=2\&category=acrcp_v1_32\&sig=AOD64_38_dy3U8tsH8NRhjk1BI1Uvux0DQ\&q\&sqi=2\&nis=4\&adurl=https://vapi.ai/?utm_cid%3D23592298723%26utm_adgroupid%3D192762299759%26utm_adid%3D798055046387%26utm_targetid%3Dkwd-4189710133%26hstk_creative%3D798055046387%26hstk_campaign%3D23592298723%26hstk_network%3DgoogleAds%26utm_source%3Dgsearch%26utm_term%3Dvapi%26utm_medium%3Dppc%26utm_campaign%3Dvapi_brand%26hsa_acc%3D4500971697%26hsa_cam%3D23592298723%26hsa_grp%3D192762299759%26hsa_ad%3D798055046387%26hsa_src%3Dg%26hsa_tgt%3Dkwd-4189710133%26hsa_kw%3Dvapi%26hsa_mt%3Dp%26hsa_net%3Dadwords%26hsa_ver%3D3%26gad_source%3D1%26gad_campaignid%3D23592298723%26gbraid%3D0AAAAA-2cnbw5m6YA9Sm-hP8rcECgBzB2N%26gclid%3DCj0KCQjwp7jOBhDGARIsABe7C4f-qDhHW788QcWCYBd583bC4Gpo4laM0LLv_BsBjRE2BD-_5ygoip0aAjfJEALw_wcB\&ved=2ahUKEwiIhd-h7M-TAxWjEDQIHfZOAX0Q0Qx6BAgcEAE).
### 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!
