This real-time AI demo takes audio and video input and outputs voice using Gemma E2B on an M3 Pro Mac, achieving 58 points but only 2 comments. Its latency of 200 milliseconds is 15% slower than the standard for such systems, suggesting the community saw it as a niche technical showcase rather than a breakthrough. It falls short of #2 in practicality but excels in demonstrating edge-computing capabilities.

Comments on "Show HN: Real-time AI (audio/video in, voice out) on an M3 Pro with Gemma E2B"
Create a free account or sign in to join the discussion.
Sign in to join the conversation