Chuddy, self-hosted media downloading, translation and OCR Telegram bot
Useful Telegram bot wrapper, but yt-dlp bots already exist in dozens of repos.
Experimentation with Voxtral-Mini-4B-Realtime-2602 and DeepL API for live translation
Microphone audio is captured in the browser as PCM and streamed over WebSockets to a Node server that pipes live segments into Mistral's Voxtral realtime API, then immediately hits DeepL for translation — a straightforward, usable demo of live STT->MT. It isn't reinventing the wheel, but the repo bundles the full flow (browser keys, Docker, server.mjs, and UI) so you can spin up an end-to-end test quickly; main downside is it's an integration demo that depends on external API keys and limits for real-world scale.
Developers and hobbyists who want a runnable demo of real-time speech-to-text + translation or a base to build translation features
It currently supports 11 languages: French, English, Chinese, Spanish, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch.
You can test on https://live-translation.alexandrelion.com/ by bringing your own API keys (Mistral + DeepL free tier)
Useful Telegram bot wrapper, but yt-dlp bots already exist in dozens of repos.
Complete Kafka pipeline demo with live dashboard, but it's a teaching repo not a product.
Local Whisper + NLLB translation with 300ms latency overlay for Discord and games.
Yet another screen OCR translator when macOS Live Text already exists.
Self-hosted HTML exports beat Navattic's platform lock-in and subscription model.
Everything runs client-side and the UI gives you real control — pick MP4 or WebM, toggle 720/1080/4K, pick gradients, and resize the camera overlay. It's not reinventing the wheel (Loom/OBS already exist), but the minimal, no-install flow plus thoughtful controls (format/quality toggles, mic and camera sizing) make it genuinely handy for quick recordings. Would be way more compelling with basic trimming or one-click cloud upload.