DigUp
Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
- 6.5k
- Swift
- MIT
- 3 wk ago
Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android and browser runtimes. Apache-2.0 SDK.
A beautiful, minimal meeting recorder for Mac. Press Start, and after Stop you get Notes and a transcript in one markdown file. On-device, free and open source.
Image text to text model, used with transformers.
Local speech-to-text for macOS on-device AI, fully private, optional cloud
Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate FunASR, vLLM and llama.cpp deployment paths.
AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
sanoTTS (सानो = 'small' in Nepali): 294k–2.27M-parameter neural TTS that runs on a $3 chip, in the browser, or in Python with low-latency streaming.
Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.
Vui Nano — a small, context-aware text-to-speech model trained on real conversations. 219M active params (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Ships with a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.
Open-source AI Agent for iOS, iPadOS and Android, designed primarily for iPadOS. On-device Linux, 3D/CAD, Notes, Office, Canvas, Python/Node.js, terminal, Git, voice and Skill Hub. BYOK AI; supported local models and native 3D editing on iOS. 开源设备端 AI 工作台,以 iPadOS 体验为核心。
Free, open source voice dictation for macOS. On-device transcription with Apple's Speech framework. No cloud/no API keys/no account.
DSH iOS 移动版:在 iPhone 和 iPad 上本机运行 DeepSeek Harness,界面完全原生,不连电脑和服务器。Run DSH (DeepSeek Harness) natively on iPhone and iPad: no computer, no server.
Open-source AI meeting notes for Mac. Records mic + system audio with no bot, transcribes on-device or via OpenAI / Deepgram / Groq, identifies speakers offline, and writes summaries that fuse your notes with the transcript. Ask your notes and get cited answers. Tauri 2 + Rust + Swift.
compact zero-shot voice-cloning TTS with state-of-the-art performance, leading voice control, real-time on-device.
Real-time on-device speech transcription + translation for macOS (Apple Silicon). Streaming ASR, speaker diarization, and live English→Chinese translation on Apple GPU/MLX — terminal CLI, no UI, no cloud.
Mila — native macOS local transcription app (whisper.cpp) with optional speaker diarization. Apache-2.0.
High-performance neural networks engine for web, built on top of TypeGPU
Fully on-device on-screen translator for macOS: region capture and live overlay, powered by Vision OCR and Apple Translation
BetterAIChat2 (BAIC2) — 本地优先的 Android AI 智能体:57 个真实设备工具(无 GMS:截屏 OCR / UI 自动化 / 离线定位 / 文件 / 网页 / 提醒 / 通知触发自动化 / 技能与子代理)、仿生记忆(别名、时间线、自省巩固、出处、时间旅行、导出/导入)、中途提问、MCP。Local-first Android AI agent with real device control. GPL-3.0-or-later.
Live, in-place screen translation for macOS — a lens that rewrites the text under it in your language, on-device.
iPhone, iPad and CarPlay client for the Hermes AI agent or any OpenAI-compatible model. Talk or type, watch it work, approve what it runs. No account, no tracking.
Ahenk: açık Türkçe metinden sese. Open Turkish text-to-speech: VoxCPM2 LoRA (Ahenk), 8.6M on-device model (Ahenk Cep), trnorm text normaliser, TR-Zor benchmark
The free, open-source meeting-notes app for your Mac — offline transcription and AI notes, free in the cloud or 100% on-device.
On-device VAD / streaming STT / TTS / diarization in C++17 (ONNX + LiteRT) with a voice-agent pipeline. Linux, Windows, Android.
Open-source, fully offline wake word / keyword spotting (KWS) inference engine — ONNX/TFLite <130KB, multi-keyword, multilingual. Train a custom wake word online with auto hard-negative mining; deploy on ESP32 / Raspberry Pi / Android / Web / Windows / macOS / Linux / Home Assistant — runs on any ONNX/TFLite-capable device.
Voice dictation that stays on your device. Open-source, local-first, and built for people who actually care about privacy.
On-device speech-to-text Flutter app powered by CrispASR (ggml / Whisper) — offline, multi-platform, AGPL-3.0.
Local-first live speech translation for macOS. On-device recognition and translation on Apple Silicon, with optional API backends.
Free, private, real-time translation for any audio on your Mac. Runs on-device with TranslateGemma and reads translations aloud. No account, no API key.
Lightweight on-device text-to-speech: flow LM over a continuous-latent codec, Rust runtime, Android/iOS/Linux/Python
1B dense to a 35B MoE in the browser, on hand-written WGSL
Runs in the browser on Hugging Face
Speaker diarization, fully in your browser
Runs in the browser on Hugging Face
A 0.6B ML-specialist model running fully in your browser
Runs in the browser on Hugging Face