Overview

OpenWhispr is a powerful, open-source, and privacy-first voice-to-text dictation application. It empowers users to transform their spoken words into text, notes, and actionable commands directly from their desktop. Designed for ultimate flexibility, OpenWhispr offers a choice between highly private, on-device transcription using local AI models like NVIDIA Parakeet and OpenAI Whisper, or leveraging cloud-based processing for maximum speed and convenience. With no data collection or telemetry, and full cross-platform compatibility for macOS, Windows, and Linux, OpenWhispr ensures your audio and data remain yours.

Key Features

• Seamless Voice Dictation: Trigger dictation with a global hotkey and have your speech automatically pasted into any application.
• Intelligent AI Assistant: Interact with leading AI models (GPT-5, Claude, Gemini, Groq, etc.) or local LLMs through a named voice assistant. Send commands, get assistance, and even have highlighted text edited in place.
• Advanced Meeting Transcription: Effortlessly transcribe Zoom, Teams, and FaceTime calls with live speaker diarization and voice fingerprinting. Integrates with popular calendar services.
• On-Device Privacy: Utilize local speech-to-text engines (Whisper, Parakeet) for fully private transcription where your audio never leaves your machine. Supports GPU acceleration on Metal, CUDA, and Vulkan.
• Robust Note-Taking: Create, organize, and semantically search notes with AI-powered actions and optional cloud sync.
• Flexible Audio Import: Transcribe existing audio and video files, or even paste YouTube links, with optional speaker detection.
• BYOK Cloud Options: Choose cloud processing for speed, with support for Bring Your Own Key (BYOK) for enhanced security and control.
• Enterprise-Ready: Offers features like SSO, SCIM, and centrally managed cloud AI access for organizations.
• Public API & Integrations: Programmatically manage your data or connect with custom AI workflows via the MCP server.

Typical Use Cases

• Enhanced Productivity: Dictate emails, documents, and code without touching your keyboard, boosting efficiency across all desktop applications.
• Secure Meeting Records: Ensure sensitive meeting discussions are transcribed locally for maximum privacy, with clear speaker identification.
• AI-Powered Workflows: Streamline tasks by using voice commands to interact with AI assistants, automating research, content generation, and more.
• Personal Knowledge Management: Capture thoughts, ideas, and information quickly into organized notes that are easily searchable and accessible.
• Content Creation: Transcribe interviews, podcasts, or video lectures efficiently, with support for batch processing and speaker labeling.
• Developer Assistance: Integrate custom transcription services or leverage the public API for building voice-enabled applications.