openwhispr
Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.
OpenWhispr is a privacy-first voice-to-text dictation application that provides an MCP server for programmatic access to notes and transcriptions. It supports both local speech recognition engines (Whisper, NVIDIA Parakeet) and cloud providers, enabling developers to integrate voice transcription capabilities into AI assistants without compromising privacy. The MCP server allows AI agents to manage notes, retrieve transcriptions, and perform semantic searches across recorded audio content.
Key Features
Use Cases
- 01Connecting AI assistants to voice transcription and note-taking capabilities via MCP
- 02Building privacy-focused voice interfaces that process audio entirely on-device
- 03Automating meeting notes retrieval and summarization through AI agents
- 04Enabling semantic search across transcribed audio libraries from AI workflows
- 05Creating voice-controlled AI assistants with local or cloud speech recognition
- 06Integrating dictation and translation features into custom AI agent pipelines
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
openwhispr — FAQ
What is the OpenWhispr MCP server?+
The OpenWhispr MCP server provides programmatic access to notes and transcriptions stored in OpenWhispr, allowing AI assistants and agents to retrieve, search, and manage voice-to-text data via the Model Context Protocol.
How do I install and connect the OpenWhispr MCP server?+
First, install and run the OpenWhispr desktop application from the releases page. Then configure your MCP client to connect to the server endpoint as documented at docs.openwhispr.com/integrations/mcp. The application must be running for the MCP server to be accessible.
Which AI clients work with the OpenWhispr MCP server?+
Any AI client or assistant that supports the Model Context Protocol (MCP) can connect to OpenWhispr. The application also supports direct integration with GPT-5, Claude, Gemini, Groq, OpenRouter, and local models through its built-in voice assistant feature.
Do I need API keys to use OpenWhispr?+
No API keys are required for local transcription using Whisper or NVIDIA Parakeet. If you choose cloud transcription or AI assistant features, you'll need to bring your own API keys (BYOK) for the respective services, or use enterprise-managed credentials.
Is OpenWhispr free and open source?+
Yes, OpenWhispr is released under the MIT license and is completely free for personal and commercial use. The source code is available on GitHub and the application includes no telemetry or data collection.
What are the system requirements for running OpenWhispr locally?+
OpenWhispr requires Node.js 24+ for development builds. For production use, download the pre-built desktop application for your platform (macOS, Windows, or Linux). GPU acceleration is optional but recommended for faster local transcription.
How do I install openwhispr?+
Open the source repository on GitHub and follow its README. openwhispr is a mcp server — MCP Agents Market links you directly to the official repo.
Is openwhispr free?+
openwhispr is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.