Text-to-Speech Demo

This demo shows how to use the JanusCore SDK's AI proxy to access Google's Text-to-Speech API.

SDK-Based Text-to-Speech: This demo uses the JanusCore SDK's AI proxy client to securely access Google's Text-to-Speech API with automatic authentication and error handling.

Checking authentication status...

Text to speak:

Voice settings: Using English (US) with the premium Chirp3-HD-Aoede voice and OGG_OPUS audio format.

Note: Google's Text-to-Speech API supports many languages, voices, and audio formats. This demo uses fixed settings for simplicity. See the Google API documentation for all available options.

Audio Output:

Audio will appear here after synthesis

SDK Features Demonstrated

AI Proxy: Secure access to Google Text-to-Speech API through the SDK
Automatic Authentication: SDK handles token management and authorization
Binary Data Handling: SDK properly handles audio file responses
Error Handling: Structured error handling with meaningful error messages
Simple API: Clean interface hiding API complexity