Nvidia PersonaPlex 7B on Apple Silicon: Full-Duplex Speech-to-Speech in Swift

Re:Nvidia PersonaPlex 7B on Apple Silicon: Full-Duplex Speec... by Serenacula on Thursday March 05, 2026 @03:34AM (#47259153)

This is really cool. I think what I really wanna see though is a full multimodal Text and Speech model, that can dynamically handle tasks like looking up facts or using text-based tools while maintaining the conversation with you.

[ Parent | on HN ]

Re:Nvidia PersonaPlex 7B on Apple Silicon: Full-Duplex Speec... by sigmoid10 on Thursday March 05, 2026 @03:43AM (#47259215)

OpenAI has been offering this for a while now, featuring text and raw audio input+output and even function calling. Google and xAI also offer similar models by now, only Anthropic still relies on TTS/STT engine intermediates. Unfortunately the open-weight front is still lagging behind on this kind of model.

[ Parent | on HN ]