Get started with the Outspeed React SDK for realtime voice AI applications
Install the React SDK using your preferred package manager:
Before using the React SDK, you’ll need:
Add your Outspeed API key to your server’s environment variables:
Never expose your Outspeed API key in client-side code. Always generate ephemeral tokens on your backend server.
The React SDK uses a SessionConfig
object to configure voice sessions:
Want to use a different voice? See all available voices you can choose from.
Option | Type | Description |
---|---|---|
model | string | Must be "outspeed-v1" |
instructions | string | System prompt for the AI assistant |
voice | string | Voice ID to use for speech synthesis |
turn_detection | object | Voice activity detection settings |
first_message | string | Optional initial message from assistant |
Now that you have the SDK installed and configured, you can start building voice AI applications: