🔍 Enhance image generation with ITO guidance for StableDiffusionXL. Test outputs seamlessly and optimize quality in a streamlined interface.

💬 Build and enjoy real-time chat with Whispr—effortlessly connect, manage conversations, and enhance your online presence with a sleek interface.

Free, fast, offline voice dictation. Record anywhere, paste anywhere. Never lose a recording.

🎙️ Open Source and Local-first AI Dictation App ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open source models, works offline, fast and accurate.

Your offline, privacy-first voice assistant framework. Transform speech into commands and actions with a powerful, scriptable rule engine.

Free, open-source, real-time dictation for Windows. Runs locally (no cloud!), uses AI, and types directly into any application via a user-friendly GUI.

A Tauri-based desktop dictation app for Windows with multiple speech-to-text providers, voice commands, and grammar correction

Native speech-to-text for Arch / Omarchy - Fast, accurate and easy system-wide dictation

Let your students train their listening comprehension and spelling skills

Private voice keyboard, AI chat, images, webcam, recordings, voice control with >= 4 GiB of VRAM.

Speak to AI • Native Linux Speech-to-Text (STT) • Offline, Privacy-Focused

GNOME Speech2Text - shell extension for speech to text (dictation) using OpenAI's automated speech recognition Whisper

Ito, smart dictation in every application

Real-time AI voice transcription in any active app on Windows OS

This SDK allows web-based apps/pages to interact with dictation devices

Privacy-first macOS transcription app with global hotkey recording. 100% on-device transcription and AI enhancement using WhisperKit + MLX, or cloud-based OpenAI. Smart paste directly into any app.

Documentation website for Knowii Voice AI

Privacy‑first, real‑time speech‑to‑text dictation. 100% local inference in Rust; hotkey to dictate anywhere (macOS, Linux, Windows).

Say - A Whisper AI Notes app

AudioWrite: Effortless voice dictation powered by Google's Gemini API. Record, transcribe, and transform rambling audio into polished, multi-language notes. PWA ready.