ElevenLabs

Show HN: HN.watch – Videos of all Hacker News posts

These AI explainers are taking over. I tried getting this working back in May. The models were okay but not quite there and it was a ton of effort. Opus 5.5 seems like the tipping point. I made an OSS framework for these for when you want to go beyond one-shoting it: https://github.com/scosman/videowright - Voiceovers: aligns animations to the voiceover, can generate voiceover with elevenlabs, or will transcribe and timestamp a real voiceover - can reorder scenes both in code, and using ffmpeg for audio. - interactive controls during authoring, can ask for micro edits or re-builds - MP4 export/encoder - Generates a video from a prompt (obvs)

Eleven v4 by ElevenLabs

Prompting Claude Opus 5.5

It's very good, yes, but I expected it to produce midjourney type results out of the box. That did not happen. The models are definitely granular stuff now though. They must be training off a ton of digital artist stroke data now. But it other cases, like the music videos, much of the magic is done by access to elevenlabs and suno apis. Edit: just saw your edit about the pdoom video. Can you share how you prompted it? Would be helpful to know.

Show HN: Cantala – a free Mexican lotería caller with recorded voices

Lotería is Mexico's bingo-with-pictures: a caller draws from 54 cards and sings a short verse (copla) for each. I built a web version: the caller shuffles and sings each card, and there's a printable tabla generator that makes non-repeating boards as a PDF in the browser (pdf-lib, no backend). Next.js on Netlify, voices from ElevenLabs. A service worker keeps the game playable offline once loaded. Feedback welcome.

Opus 5.5 is good at explainer videos

There isn’t that much to say. Start with an empty directory, put the XKCD image in it, add your ElevenLabs API key, and set up a Python virtual environment. Install ffmpeg. Then start Claude. From that point on, it’s mostly prompting and evaluating the results. Like any good engineer, you shouldn’t simply start with “Create a video from this comic.” Instead, take a step-by-step approach: discuss the visual style, animations, ask for audio examples, create a script, and then develop a storyboard (ask for a .html document). The important part is to break the whole generation process down into small, manageable steps. I also used the brainstorming skill from Superpowers for the discussions. It makes the whole process much easier when the AI asks the questions and I just have to answer them. …