▪ claudecodedaily

I got tired of switching between ChatGPT, Claude, and Luma, so I built my own "AI Command Center" with a Podcast Generator, Vision-to-Code, and Live Voice Hey everyone, I’ve been working on a project called AskSary because I wanted a single interface that could handle text, code, voice, and video without constantly tab-switching. I wanted something that felt less like a chatbot and more like a futuristic OS. I’ve spent the last few months adding every feature I personally wanted as a power user. Here is what I’ve managed to pack into it so far: The "Command Center": A popup grid of tools including a Regex Generator, Git Guru, and an "ELI5" explainer. Vision-to-Code: I can upload a screenshot of a UI, and it writes the HTML/Tailwind code and renders a preview instantly in a built-in "Code Lab." AI Podcast Studio: It takes a chat history or a topic, generates a 2-person script (Host vs. Guest), and voices it using OpenAI's TTS. Real-time Voice Mode: I built a "Quantum Nebula" visualizer (it’s an orb that reacts to volume) for hands-free voice chat. Multi-Model Support: It switches between models like GPT-5 Nano, Gemini, and Grok 3 depending on whether I'm asking for creative writing or stock market analysis. Video Generation: Integrated Luma Dream Machine to generate cinematic clips directly in the chat. Document Analysis: I can upload PDFs, Audio files, or Graphs, and it runs a "Deep Dive" analysis to extract insights. The whole thing is wrapped in a glassmorphism UI with 4K live wallpapers because I hate boring interfaces. I’d love for you guys to tear it apart (or try it out) and let me know what other "micro-tools" I should add to the Command Center. https://t.co/4b8SCjqZVk https://t.co/aRs5vItNIl @grok @OpenAI @googledevs @GooglePlay