Hey Product Hunt!

We tried something a little crazy.

What if you could create a video ad or content video in seconds

Hey Product Hunt! I'm the founder of Kinetic Mingle, I've been looking at threads here for a while and figured it's time to say hi!

What I Built

Kinetic Mingle is a video-first dating platform for adults 21+. We focus and lead with the the personal interaction part of online dating. It's front and center of our platform. Instead of static photos, filtered glamor shots and robotic swiping, users connect directly through video chat, video messaging, voice notes, and verified profiles. Our AI coaching assistant is a highlight feature. It uses adaptive learning tailored to individual user activity. You get your own personalized AI agent. Its a real gem!

I was paying for 5 AI subscriptions: Claude Pro, Cursor Pro, ChatGPT Plus, Copilot, and Gemini Advanced. $90/month total.

I assumed I was using all of them heavily. Turns out I was wrong.

Hi Product Hunt
I'm building Sokuji, an open-source real-time AI voice translation tool. Speak your language in a video call, and your words are translated and spoken in the other person's language live.
Why Sokuji?
Privacy-first, local-first.
Sokuji can run the entire speech recognition translation text-to-speech pipeline 100% locally in your browser using WebAssembly and WebGPU. No cloud, no API keys, no data leaving your device ever. Your conversations stay yours. Cloud providers (OpenAI, Gemini, etc.) are available as options, not requirements.
Just install a browser extension. That's it.
No desktop app download, no signup, no setup wizard. Install the Chrome/Edge extension, open your Google Meet / Teams / Zoom call, and start translating. It works in the browser sidebar right where your meeting already is. (A desktop app with system audio capture is also available for power users, but most people won't need it.)
---
What it can do
Offline local inference
- 12+ ASR models (SenseVoice, Whisper WebGPU, Paraformer, Parakeet TDT...)
- 49 Opus-MT translation pairs + Qwen 3.5 for multilingual translation
- Multiple TTS engines (Piper, Matcha, MeloTTS)
- Smart model variant selection based on your GPU capabilities
7+ cloud providers (optional)
OpenAI Realtime (GA, WebRTC), Google Gemini, Volcengine (ByteDance), Palabra AI, any OpenAI-compatible endpoint, or our hosted Kizuna AI option. Bring your own API key if you want lower latency or higher quality.
Modern audio pipeline
AudioWorklet-based low-latency processing, built-in noise suppression, dynamic device switching mid-session, cross-platform system audio capture, virtual audio devices on macOS/Windows.
35+ UI languages the app itself speaks your language too.
Other highlights: text input translation, karaoke-style TTS highlighting, Push-to-Talk, auto-updater (desktop), Stripe token wallet for hosted API.
---
What's next
The local-first approach is working, but we want to push it much further:
- TranslateGemma 4B Google's 55+ language any-to-any translation model via WebGPU, replacing current English-pivot Opus-MT limitation ([#123](https://github.com/kizuna-ai-lab...))
- Voxtral Mini 4B Mistral's 13-language real-time streaming ASR, <500ms latency ([#125](https://github.com/kizuna-ai-lab...))
- Native inference in Electron bypass WASM overhead, unlock GPU acceleration for significantly faster local performance ([#129](https://github.com/kizuna-ai-lab...))
- More meeting platforms: Webex, Jitsi, GoTo, RingCentral
- Windows & macOS code signing, Linux AppImage + Flatpak
---
Links
- Website: https://sokuji.kizuna.ai
- GitHub: https://github.com/kizuna-ai-lab...
- Chrome Web Store: https://chromewebstore.google.co...
- Desktop download (optional): https://github.com/kizuna-ai-lab...
Built by Kizuna AI Lab. Feedback, issues, and PRs welcome. If you deal with multilingual meetings or care about keeping your conversations private, I'd love to hear from you.

Hey everyone!

I was spending 3+ hours every day manually sending WhatsApp messages to leads and customers.

So I built TrueChattr a WhatsApp automation tool that handles:

• Bulk messaging

• Auto-replies

• Lead management

It's completely free to try right now.

Happy to answer any questions about how it works!

www.truechattr.in

I m one of the creators of Lingogrind, a small startup we re building to help people learn German and prepare for official exams (Goethe, telc, TestDaF).

We noticed that many learners struggle with two things:
structured exam preparation
consistent practice with real exam-style exercises

So we started building Lingogrind to make exam prep more structured, focused, and a bit more motivating.

Right now we re in early beta and looking for a small group of testers who are learning German or preparing for an exam.

Hi guys,

I'm currently an intern trying to learn how builders and marketers find real user insights.

A few weeks ago I tried doing "market research" the way people often recommend:
Go to TikTok, find posts related to a niche, and read the comments.

At first it sounded simple.

Here's something I noticed while building Auralify that I can't stop thinking about.

When a user asks ChatGPT, Meta AI, or Gemini about a company a brand reputation, a CEO, a product recall they get a confident, synthesized answer. No sources listed. No timestamp. No "this might be outdated." Just an answer. And users trust it. Recent studies suggest people now trust AI assistant responses more than the top organic search results.

Hey everyone,

Final year student here. Built Knot to solve my own problem - I had 2,000+ saved posts on X and remembered none of them.

What it does:

- Auto-saves tweets when you bookmark on X