Stars
Implementation of the OmniVoice inference model from k2-fsa on Rust
Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetil…
NeMo-based speaker diarization over 4-speakers
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Andr…
Speakr is a personal, self-hosted web application designed for transcribing audio recordings
Kokoro Language Model Training Script for Russian (Ruslan Corpus)
C++ port of Microsoft VibeVoice built on ggml
A fully local and private Speech-To-Text app with cross-platform support, speaker diarization, Audio Notebook mode, LM Studio integration, and both longform and live transcription.
Speaker diarization for Python — "who spoke when?" CPU-only, no API keys, Apache 2.0. ~10.8% DER on VoxConverse, 8x faster than real-time.
Vault-native meeting capture. Timestamped notepad + local transcription + Claude Code skill that distills into Obsidian notes connected to your existing thinking.
LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratc…
Antigravity CLI brings the reasoning, execution, and orchestration capabilities of Antigravity agent harness directly into your terminal.
The open-source AI voice studio. Clone, dictate, create.
Voice-driven writing, input, and cross-app work for your desktop.
Pure Rust Whisper speech-to-text inference engine. Zero C/C++ dependencies.
Rust implementation of Qwen3-TTS speech synthesis
very fast speech-to-text, diarization, streaming (even in CPU) with NVIDIA Parakeet in Rust
The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription
FluidVoice - Fastest macOS Offline Dictation app - Voice to Text fully Local. One ⭐ takes us a long way :))
🦋 A tool to manage versioning and changelogs with a focus on monorepos
Select a portrait, click to move the head around (please use your own space / GPU!)
Lightweight screen annotation tool — press a hotkey to draw, highlight, and annotate anywhere on your desktop.
The best-benchmarked open-source AI memory system. And it's free.
A collection of lightweight, strongly-typed TypeScript utility libraries — schema validation with type inference, async helpers, deep object operations, object mapping, job scheduling, and more.