Generate engaging UGC shorts from a product URL
Hey HN! Sophia here from Glato AI. For the last 3 months, we've been heads down building a cutting-edge short video ads generator. We got the idea because creating UGC shorts for user acquisition is a massive pain. Hiring creators costs $100+ per vid and takes forever. So we thought, why not use AI to automate this? That's where Glato AI comes in - it's one of the most advanced AI workflows we've built. Just feed it a product URL and it'll analyze the details, find related media, understand what's being shown, write a script, create an expressive avatar, lay out each scene with b-roll and…
What it does
In the maker’s words, at launch
Hey HN! Sophia here from Glato AI. For the last 3 months, we've been heads down building a cutting-edge short video ads generator. We got the idea because creating UGC shorts for user acquisition is a massive pain. Hiring creators costs $100+ per vid and takes forever. So we thought, why not use AI to automate this? That's where Glato AI comes in - it's one of the most advanced AI workflows we've built. Just feed it a product URL and it'll analyze the details, find related media, understand what's being shown, write a script, create an expressive avatar, lay out each scene with b-roll and effects - the whole pipeline. We're excited to launch the alpha today! It's still pretty early, so hit us up with any issues or improvement ideas. We'll be iterating like crazy based on your feedback. Give Glato AI a try and let us know what you create!
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
