Note
Before starting, make sure you have created a Cloud account, installed the LiveKit CLI, and have authenticated or manually configured your LiveKit project of choice.
The LiveKit CLI can help you bootstrap applications from a number of convenient template repositories, using your project credentials to set up required environment variables and other configuration automatically. To create an application from a template, run the following:
lk app create --template <template_name> my-app
Then follow the CLI prompts to finish your setup.
The --template flag may be omitted to see a list of all available templates, or can be chosen from a selection of our first-party templates:
| Template Name | Language/Framework | Description |
|---|---|---|
| agent-starter-python | Python | A starter project for Python, featuring a simple voice agent implementation |
| voice-assistant-frontend | TypeScript/Next.js | A starter app for Next.js, featuring a flexible voice AI frontend |
| agent-starter-android | Kotlin/Android | A starter project for Android, featuring a flexible voice AI frontend |
| agent-starter-swift | Swift | A starter project for Swift, featuring a flexible voice AI frontend |
| agent-starter-flutter | Flutter | A starter project for Flutter, featuring a flexible voice AI frontend |
| agent-starter-react-native | React Native/Expo | A starter project for Expo, featuring a flexible voice AI frontend |
| agent-starter-embed | TypeScript/Next.js | A starter project for a flexible voice AI that can be embedded in any website |
| token-server | Node.js/TypeScript | A hosted token server to help you prototype your mobile applications faster |
| meet | TypeScript/Next.js | An open source video conferencing app built on LiveKit Components and Next.js |
| multi-agent-python | Python | A team of writing coach agents demonstrating multi-agent workflows |
| outbound-caller-python | Python | An agent that makes outbound calls using LiveKit SIP |
Tip
For more information on templates, see the LiveKit Template Index.