Python
Local ElevenLabs on Your Own Hardware with VoiceStudio
VoiceStudio brings local ElevenLabs-quality voice synthesis, cloning, and transcription to your own hardware—no cloud, no subscriptions, just open-source power.
#speech-to-text
5 projects JavaScript
All Local AI Models in One Window — A Look at Uncensored Local Studio
A look at Uncensored Local Studio, a unified desktop client that combines Stable Diffusion, language models, speech recognition, and text-to-speech into a single app.
JavaScript
How to Turn Voice into Code and Notes Without Clouds and Prying Eyes
OpenWhispr is an open-source voice-to-text app that runs entirely locally, offering dictation, meeting transcription, and AI agents without cloud dependency.
C-plus-plus
How to Run Speech Recognition on Any Hardware Without the Pain and Python Dependencies
transcribe.cpp is a lightweight C/C++ library for speech recognition that runs on any hardware without Python dependencies. Supports 16 model families, multiple backends, and GGUF quantization.
Python
MLX-Audio — When Your Apple Silicon Mac Learns to Speak and Listen
MLX-Audio brings lightning-fast TTS, STT, and STS capabilities to Apple Silicon Macs. Built on Apple's MLX framework, it offers Whisper, Kokoro, voice cloning, and more—all running locally without cloud costs.