What I Built
Omni-VRAM is an open-source voice AI platform with 28 modules.
GitHub: https://github.com/Liangchenxu/Omni-VRAM
Features
Speech Recognition: Whisper with 5 backends (faster-whisper, whisper.cpp, ONNX, TensorRT, OpenAI API)
What I Built Omni-VRAM is an open-source voice AI platform with 28 modules. GitHub:...
Omni-VRAM è un voice AI platform open-source con 28 moduli, Whisper multi-backend, <200ms streaming, diarization, emotion, TTS e meeting assistant. Stack self-hosted production-ready (REST/gRPC, Docker) che riduce costi e lock-in vs SaaS proprietari.
What I Built
Omni-VRAM is an open-source voice AI platform with 28 modules.
GitHub: https://github.com/Liangchenxu/Omni-VRAM
Features
Speech Recognition: Whisper with 5 backends (faster-whisper, whisper.cpp, ONNX, TensorRT, OpenAI API)

I built a real-time Voice AI assistant that listens, thinks, and talks back — using entirely...

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built Ovela AI...

Eighteen months ago, we thought we were building a simple voice memo app. We were wrong about the...

Voicebox combines ElevenLabs voice cloning and WisprFlow dictation into a local-first desktop app. 28.5K GitHub stars, MIT…

Six posts this week. EU watermarking, emotion prompts, open source voice agents, AI coding one year on, a raccoon heist game, and…

I benchmarked local voice-cloning models across English, German, Modern Standard Arabic, Spanish, and...