Show HN: Real-time AI (audio/video in, voice out) on an M3 Pro with Gemma E2B

Post by spwa4 » Tue, Apr 07, 2026, 7:18 AM UTC

karimf wrote: post #40

spwa4 wrote: post #35

I've been trying to do this, but I can't get voice recognition to work fast enough (meaning live) with Gemma E2B, on either an M1 max (64GB), a 5060 Ti (16Gb) or a SnapDragon 8 Gen2. Any pointers?

What's your average response time with M1 max and what's the target?

Post by 3abiton » Wed, Apr 08, 2026, 3:32 PM UTC

logicallee wrote: post #12

It might interest people to know you can also easily fine-tune the text portion of this specific model (E2B) to behave however you want! I fine-tuned it to talk like a pirate but you can get it to do anything you have (or can generate) training data for. (This wouldn't make it to the text to speech portion though.) So you can easily train it to act a certain way or give certain types of responses. Video: https://www.…

Post by crsAbtEvrthng » Mon, Apr 13, 2026, 11:59 AM UTC

matula wrote: post #38

crsAbtEvrthng wrote: post #22

If I run this without internet connection it says "loading..." at the bottom of the localhost site and won't work. If I run this with internet connected it works flawlessly. Even if I disconnect my internet afterwards it still goes on working fine. Why there has to be an internet connection established at the time I open the localhost site when all of this should be working purely on device? Despite of this, I am rea…

the index.html is loading remote js files: https://github.com/fikrikarim/parlor/blob/main/src/index.htm... I saved them locally and changed the reference, and it worked perfectly.