gpt-omni/mini-omni

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

3 best points · 0 comments · 1 Hacker News post · 3,582 GitHub stars · View on GitHub

Hacker News discussions

• Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming (3 points, 0 comments, by thenameless7741, 2024-09-03)