Nuvotion-Visuals / Harmony3

1 stars 0 forks source link

Implement Streaming Text-to-Speech for Active Message Generations #42

Open tom-leamon opened 6 months ago

tom-leamon commented 6 months ago

Overview

We aim to enhance the user interaction with our large language model (LLM) by introducing an optional mode where text-to-speech (TTS) begins as soon as the first sentence of a generation is complete. This feature will provide real-time auditory feedback as messages are being generated, improving the dynamism and interactivity of the application.

Current Implementation

Proposed Implementation

Server-Side
Client-Side

Goals

Additional Considerations

Next Steps