A React starter template for building real-time conversational AI agents using VideoSDK.
- Voice & Video Support: Real-time audio and video communication.
- AI Agent Integration: Interact with an AI agent with real-time responses.
- Live Transcription: Display ongoing conversation transcripts.
- Screen Sharing: Share your screen during sessions.
- Device Management: Switch between audio and video input/output devices.
Before you begin, ensure you have the following installed:
Use the following steps to run the project locally:
git clone https://github.com/videosdk-live/agent-starter-app-react.git
cd agent-starter-reactnpm install
# or
yarn installCreate a .env file in the root directory by copying the example:
cp .env.example .envUpdate the .env file with the following values:
AUTH_TOKEN=your_videosdk_auth_token
AGENT_ID=your_agent_id
MEETING_ID=your_meeting_id (optional)
VERSION_ID=your_version_id (optional)Tip
You can obtain your AUTH_TOKEN from the VideoSDK Dashboard.
npm run devThe application will be available at http://localhost:5173.
| Variable | Description | Required |
|---|---|---|
AUTH_TOKEN |
VideoSDK authorization token | Yes |
AGENT_ID |
ID of the AI agent to connect with | Yes |
MEETING_ID |
Meeting ID to join (optional) | No |
VERSION_ID |
Version ID of the AI agent (optional) | No |
Built with ❤️ by VideoSDK