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…

StepFun, the Shanghai lab that builds LLMs that punch above their weight, just turned that same energy on voice.

Together AI launches the fastest voice AI stack: streaming Whisper STT, serverless open-source TTS (Orpheus & Kokoro), and…