v1.4.1 is out. Here's what shipped and what broke along the way.
The headline feature: Vois CLI and AI agent automation
This one is for the developers and automation folks. Vois now ships a CLI binary inside the app installer. AI agents (Claude Code, Claude Desktop, ChatGPT Desktop, Codex, Cursor, Gemini) can drive it directly.
We host skill files at vois.so/skills that teach agents the full command set: create projects, write scripts, assign voices, generate audio, export with mastering profiles. An agent reads the skill file and knows how to run your entire voice production pipeline from the terminal.
I've been thinking a lot about what separates AI products that people actually stick with from those they try once and forget. The pattern I keep noticing is that the ones that win aren't necessarily the most powerful they're the ones that feel like they understand your context.
Think about it: most AI tools today are essentially fancy command lines. You give them an instruction, they spit out a result. But the products gaining real traction are the ones that remember what you care about, adapt to how you work, and meet you where you are emotionally not just functionally.
Hey PH community. Yesterday we launched ClawSecure and landed #2 Product of the Day
ClawSecure is the free security scanner for OpenClaw AI agent skills. But I'm not here to pitch. I just want to share real traffic numbers and what I actually learned from our Product Hunt launch, so it's useful for other makers planning theirs
When you re-record a demo, it's rarely because the capture is broken. It's usually something small, maybe a line you didn't like, a weird pause, or the webcam overlay blocking part of your demo.
And at that point, you're either re-recording the whole thing or dragging the file into a separate editor just to fix one moment.
Cyber risk today is mostly documented in spreadsheets, PDFs, and slide decks formats that are hard to version, automate, or integrate with tooling.
CRML (Cyber Risk Modeling Language) aims to represent cyber risk as structured, machine-readable models instead of documents. This allows risk scenarios to be version-controlled, generated by tools, and executed through simulations.
When I first started, I believed that as long as I built a great product, it would naturally become popular. But as I zoomed out, I realized the market is incredibly competitive. Having a good product alone isn t enough to truly convince users.
That s when I began building my presence on social media creating content about myself, sharing my journey, and talking about the product I m building. I ve come to see this as a very effective way to build trust and spark genuine interest not only in what I make, but also in who I am as a founder.
Native macOS Support: A fully optimized, high-performance Mac version that matches our Windows experience.
Selection Context (Experimental): Move beyond just words. When you select text, Everywhere now captures the surrounding context, drastically improving the accuracy of translations and explanations.
Integrated Settings: No more digging through menus. Open and tweak your settings directly from the chat window.
Smarter Tools: Enhanced file encoding detection and optimized web search prompts for more precise answers.
you can follow drift's progress and other cool stuff im making on x - https://x.com/divikkk1 Ive Thought about some more features for drift and how they can help creators , happy recording !
