> ## Documentation Index > Fetch the complete documentation index at: https://docs.rime.ai/llms.txt > Use this file to discover all available pages before exploring further. # Vapi > Connect Rime TTS to Vapi voice agents. export const IntegrationHeader = ({partnerLogo, partnerAlt = "Partner logo", rimeLogo = "/images/rime_logo_new.svg", rimeAlt = "Rime logo", rimeHeight = "40px", partnerHeight = "40px"}) =>
{rimeAlt} + {partnerAlt}
; Vapi demo [Vapi](https://vapi.ai) is an API-first platform for building, testing, and deploying AI voice agents. It handles telephony, orchestration, and integrations so you can focus on your agent's behavior. Paired with Rime's ultra-realistic voices, you get natural-sounding conversations with sub-200ms latency. This guide walks you through creating a basic voice assistant with Vapi and Rime. ## Prerequisites To follow this guide, you need: * A [Vapi](https://dashboard.vapi.ai) account * A Rime [API key](https://app.rime.ai/tokens) (optional) ## Step 1: Create the assistant From the [Vapi Dashboard](https://dashboard.vapi.ai), navigate to **Assistants** and click **Create Assistant**. Vapi assistants page with Create Assistant button ### 1.1 Select a template Give your assistant a name, select **Blank Template**, and click **Create Assistant**. Create assistant modal ### 1.2 Configure the model In the **Model** tab, select your preferred LLM provider. Any option should work, but models with lower latency enable better conversational flow. Add a **First Message** to enable your assistant to begin conversations. Configure a **System Prompt** to define your agent's personality and behavior. The system prompt can be as complex or simple as you like. For example: ``` You are a helpful voice assistant. Keep your responses short and conversational. No more than 2-3 sentences. Be friendly and natural. ``` Alternatively, use the **Generate** button and get AI help to create a well-structured prompt. Model tab configuration ### 1.3 Configure the voice In the **Voice** tab, configure your assistant to use **Rime AI** as the **Provider**. Select the **Voice** that you want your assistant to use. Learn more about Rime's voices on the [Voices](./voices) page. Set the **Model** to **Arcana** to use the latest Rime model with the most realistic voices. Voice tab with Rime AI provider selected ### 1.4 Configure the transcriber Finally, in the **Transcriber** tab, select your preferred speech-to-text (STT) **Provider** and click **Publish**. Transcriber tab configuration ### 1.5 Publish the assistant In the publishing popup window, select **Skip and Publish**. Publish popup window ## Step 2: Add your API keys to Vapi (optional) Vapi provides API access to all its supported models via its billing plans. However, if you already have a subscription plan for one or more of your assistant's configured providers, you can enable the assistant to access them instead of using integrated Vapi billing: Under the **Build** heading, click **More** and select **Integrations**. Then, find your providers and add your API keys. Integrations Vapi stores API keys securely and automatically grants your assistants access to them. Rime API key integration ## Step 3: Test your assistant The above steps create the most basic assistant using Rime's voices. Click **Talk to Assistant** in the dashboard to start a conversation in your browser. Vapi demo ## Next steps To further customize your assistant, you can: * **Try different voices:** Audition other voices like `celeste`, `orion`, and `andromeda` at [app.rime.ai](https://app.rime.ai). * **Add a phone number:** Provision a contact number in the Vapi dashboard and assign it to your assistant for telephony * **Create a workflow:** Program your assistant to do complex tasks using [Vapi Workflows](https://dashboard.vapi.ai/workflows). * **Customize the personality:** Update the system prompt to match your use case.