Tag
A tweet promotes Part 2 of a masterclass series on maximizing the Hermes Agent Desktop app, detailing features such as sessions, composer, voice conversation, subagents, and code review functionality.
The article demonstrates voice conversations between Gemma 4 models on GPU and Jetson Orin hardware, using the open-source Cortexist Little Gemma engine for efficient inference with lip sync and gestures.
A user highlights a new feature from SpaceXAI that allows screen sharing with a voice AI model in conversation mode, enabling the model to see and assist with browser activities.
OmniFlatten is a novel GPT-based model that enables real-time, full-duplex spoken dialogue through a multi-stage post-training technique that integrates speech and text without altering the original architecture.
OpenAI has released GPT-Live-1, a full-duplex AI model in the API that enables real-time voice conversations with background noise handling and integration with backend reasoning models.