OpenWhispr/openwhispr

Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

What it solves

OpenWhispr is a privacy-first voice-to-text tool that replaces manual typing with AI-powered dictation, meeting transcription, and note-taking. It eliminates the need for cloud-dependent transcription services by offering fully local, on-device processing options to ensure audio data remains private.

How it works

The application integrates several high-performance speech-to-text (ASR) models—such as Whisper, NVIDIA Parakeet, and Orukeet—and runs them either locally via whisper.cpp and sherpa-onnx or through cloud providers. It uses a global hotkey system to capture audio and paste text directly into any active application. For meetings, it auto-detects calls from platforms like Zoom and Teams, applying speaker diarization and voice fingerprinting to identify who is speaking.

Who it’s for

It is designed for professionals, students, and teams who need efficient voice-to-text workflows, secure meeting records, and AI-assisted note organization without sacrificing privacy.

Highlights

  • Privacy-First Dictation: Local transcription models ensure audio never leaves the device.
  • AI Agent Integration: Direct voice commands to LLMs (GPT-5, Claude, Gemini, etc.) with optional screen context via screenshots.
  • Meeting Intelligence: Live speaker diarization and voice fingerprinting for automatic meeting transcription.
  • Cross-Platform Support: Native apps for macOS, Windows, and Linux.
  • Flexible Infrastructure: Supports both local GPU-accelerated inference (Metal, CUDA, Vulkan) and cloud providers.
  • Extensibility: Includes a public API and an MCP server for programmatic note management.

Related

  • Dispatch
    BetterWispr 0.0 Release – Free Open‑Source Local Dictation for macOS

    BetterWispr 0.0 is a free, open‑source macOS app that provides offline, local‑only dictation with customizable cleanup, styles, and meeting‑note features, and it has sparked a lively discussion about local speech models and competing tools.

  • Project
    Beingpax/VoiceInk

    VoiceInk is a macOS‑only, offline speech‑to‑text app that uses local Whisper‑based models (via whisper.cpp and transcribe‑cpp‑swift) to provide near‑instant, privacy‑preserving transcription, context‑aware modes, custom dictionaries, global shortcuts, and a built‑in AI assistant. It’s open‑source under GPL‑v3, installable via Homebrew or from source, with optional paid licensing for updates and support.

  • Project
    ideaplexa/voicetypr

    Voicetypr is an open‑source, offline‑first dictation app for macOS and Windows. It captures speech via a global hot‑key, transcribes locally with Whisper (and Parakeet on Apple Silicon) or optionally via cloud STT services, can clean up the text with LLMs, and inserts the result at the current cursor. A companion CLI lets scripts or AI agents use the same transcription pipeline, returning plain text or JSON. The app is built with Tauri (Rust backend) and React, offers LAN‑based private transcription servers, and is released under AGPL‑3.0.

  • Project
    TypeWhisper/typewhisper-mac

    A system-wide speech-to-text and AI text processing utility for macOS that supports local and cloud transcription engines with customizable AI workflows.

  • Project
    goodroot/hyprwhspr

    hyprwhspr is a native Linux speech‑to‑text app that runs as a system‑wide service. It uses local models (Whisper, Cohere, Parakeet, Qwen3‑ASR, etc.) for near‑real‑time dictation, optionally falls back to cloud APIs, and integrates with Wayland/X11 desktops, status bars, and a themed visualiser. Install via the AUR or a one‑line script, configure with `hyprwhspr setup`, then toggle dictation with `Super+Alt+D` to have transcribed text auto‑pasted into any window.