Live data from Hacker News

Show HN: I made a drop-in Voice Mode for AI startups

1–2 of 2 posts

Show HN: I made a drop-in Voice Mode for AI startups

Post by andupotorac » Thu, Nov 20, 2025, 9:36 AM UTC

Text inputs are too slow for complex prompting if you're vibe coding or generating media. I built a full-stack Voice Mode component (UI + logic + transcription) for React/Next.js. It handles the awkward browser audio stuff so you don't have to.

Also used Gemini 3 to generate that entire page in one prompt. :-)

Show HN: I made a drop-in Voice Mode for AI startups
memoreco.com

Re: Show HN: I made a drop-in Voice Mode for AI startups

Post by andupotorac » Mon, Nov 24, 2025, 2:06 PM UTC

Added support for Playwright, so that the LLM can get the screenshot of the page the user wants to copy. While this seems like a small thing, what is required to build it, and what the difference in the output is are quite large.

Here are some examples of different tools, compared to Same.dev that also captures screenshots of pages - and all the others.

https://x.com/andupoto/status/1992928743925690382

Post reply on HN