offline

Offline voice input panel & keyboard with punctuation for Android.

Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST API and MCP support for AI clients.

A complete private computer on a USB stick. PAI is a bootable Debian 12 Linux distro that runs Ollama locally on any x86_64 or ARM64 machine — full desktop, local AI, hardened networking, all in RAM. Plug in, boot in seconds, work anywhere, pull the stick and nothing stays behind. Your AI on your hardware, no cloud, no accounts. https://pai.direct

Windows 离线语音输入：按 F2 说话，文字回到当前光标；不上传、可恢复、长语音不丢尾。

A collection of zipped Ollama models for offline use. Simply download, extract, and set up your desired model anywhere.

The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives your live graph: edits, workflows & installs in natural language. The panel UI for comfyui-mcp, the agent-native control plane for ComfyUI.

Free offline voice-to-text for macOS. Push-to-talk, works in any app.

NOVA is a customizable voice assistant made with Node.js.

Secure, locally-run Retrieval-Augmented Generation system for document-based question-answering, utilizing Llama 3, Mistral, and Gemini models with a user-friendly Streamlit interface.

An automatic speech recognition API

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.

Open-source offline voice dictation — a free alternative to Typeless. 100% local, zero internet, ideal for air-gapped & classified environments. SenseVoice + DirectML GPU, ~34MB, hotkey-driven. 纯离线语音输入，Typeless 免费平替，数据永不出设备，适合党政机关等涉密场景。

100% free, local & offline voice assistant with speech recognition

Offline Voice Recognition Module for MagicMirror²

Open-source, offline voice-to-text for macOS. Hold a hotkey, speak, text appears. Private on-device dictation with multiple speech engines.

Off Grid AI — private, on-device AI. Run open models (text, vision, image, voice) locally through one OpenAI-compatible gateway. No cloud, no accounts, no API keys.

Give your tools a voice — speech to text and back, 25 languages, up to ~19× faster than Whisper. On your machine.

Voice-first macOS menu bar app: dictate, voice-edit clipboard, read aloud, AI chat with Google/Trello tools, and live meeting notes. Bring your own keys (Gemini, GPT, Grok) or run offline with Whisper.

AI-powered photography workflow automation

Free, offline voice dictation for macOS, Windows & Linux — hold a key, speak, and your words appear at the cursor. Local Whisper, learns your vocabulary, no subscription. A Wispr Flow alternative.