Skip to main content
In this quickstart, you’ll build a voice agent with LiveKit and Prism, and talk to it from your browser. The agent answers questions about a made-up cafe. When you ask about opening hours, it calls a function in your code to look them up. A typical LiveKit voice agent chains three plugins: speech-to-text, an LLM, and text-to-speech. Prism replaces all three. It listens, knows when you’ve finished talking, and answers out loud. If you’ve used OpenAI Realtime with LiveKit, Prism takes the same place in your agent. LiveKit still carries the audio between your browser and your agent.

LiveKit's video on Prism: Your voice agent just said the wrong thing. Here's how to stop it.

What you’ll need

  • A Rime API key. If you don’t have one, sign up for Rime to create one. With LiveKit Inference, you can skip it.
  • A LiveKit Cloud project, with its URL, an API key, and the key’s secret. Your own LiveKit server works too.
  • uv 0.9.26 or later, which installs Python for the project if needed. The Rime SDK needs Python 3.11 or later.
  • A browser with a microphone.

Build the agent

1

Create the project

Create a Python project:
Install LiveKit Agents and the Rime plugin with its realtime extra:
To keep Agents 1.7.1, install the Rime plugin from this pinned commit in LiveKit’s official repository instead of the PyPI package.Add this setting to your project’s pyproject.toml so uv keeps the published Agents core:
pyproject.toml
Install the plugin with Agents 1.7.1:
2

Set your credentials

Create .env.local in your project folder with your own values. Your LiveKit Cloud project’s settings show its URL and let you create an API key and secret:
.env.local
3

Save the agent

Save this script as agent.py in your project folder. It registers an agent named prism-agent, which starts a Prism session in the aurora voice and greets the caller in each room it joins.
agent.py
Three parts control the conversation:
  • rime.realtime.RealtimeModel: connects the agent to Prism and selects its voice.
  • @function_tool: lets Prism request the cafe’s opening hours from your code.
  • generate_reply(): asks Prism to greet the caller first.
4

Start the agent

Run it in development mode from your project folder:
The agent connects to your LiveKit project and logs registered worker with "agent_name": "prism-agent". Leave it running. You can ignore the warning that dev is deprecated, or use lk agent dev from the LiveKit CLI instead.
5

Talk to the agent

  1. In LiveKit Cloud, open your project’s Agent Console.
  2. Set the agent name to prism-agent.
  3. Select Start a session.
  4. When your browser asks, allow microphone access.
Prism greets you as soon as you join, so you know the session works. Now ask, “What time do you close today?”The agent should answer that the cafe opens at 8 a.m. and closes at 4 p.m. Then interrupt its next reply to check interruption handling.If the call doesn’t work:
  • The agent never joins: check that the console’s agent name is prism-agent and the terminal shows registered worker.
  • The agent joins but stays silent: look for a Rime plugin error in the terminal, and look up its code in Errors and limits.

How Prism changes a LiveKit agent

Prism handles the whole conversation. Keep these constraints in mind when adapting the example: For settings, tool restrictions, retries, playback, and history, use the LiveKit plugin reference. To choose your own transcription and language model, use the LiveKit TTS quickstart.

Use LiveKit Inference

You can also reach Prism through LiveKit Inference. It signs in with your LiveKit API key and secret instead of a Rime key, and LiveKit Cloud bills the usage. In the agent above, replace the line that creates the model:
Keep the rest of the agent as it is, and leave RIME_API_KEY out of .env.local. LiveKit’s Rime Prism page lists the Inference options.

Use your own LiveKit server

On your own server, which has no Agent Console, send the agent to a room with the LiveKit CLI:
  1. In .env.local, set LIVEKIT_URL, LIVEKIT_API_KEY, and LIVEKIT_API_SECRET to your server’s values, and start the agent the same way.
  2. Send the agent to a room. Pass your server details with --url, --api-key, and --api-secret, or set the same three variables in your shell.
  3. Join the prism-test room from any LiveKit client with a microphone, such as an app built with LiveKit’s frontend SDKs.

Next steps

Now that your agent answers, you can: