OpenWhispr
An open-source, free, cross-platform system-level voice dictation tool supporting macOS, Windows, and Linux. It offers two modes—pure dictation and AI assistant—and integrates with multiple speech-to-text and language model services including OpenAI, Anthropic, Google Gemini, and Ollama.
Timeline (last 90 days)
OpenWhispr is an iOS app released on Product Hunt, whose core selling points are being 100% open source, free, and completing transcription entirely on-device.
OpenWhispr completes transcription locally, audio does not need to be uploaded to any server, there is no usage limit, and no account registration or subscription payment is required.
If OpenWhispr uses a permissive license, the barrier for community forks is lower, but it also means others can package it into a closed-source product; if it uses a copyleft license, it can ensure improvements are contributed back to the community, but it will restrict the ways of commercial integration.
As of the time of inclusion, OpenWhispr has 84 votes and 4 comments on Product Hunt, ranking 14th.
OpenWhispr's AI assistant mode can use selected text as context to perform instructed transformations, such as converting text to uppercase or rewriting Python if-else code into match-case syntax.
OpenWhispr's underlying architecture separates speech recognition and language model processing into two independent pipelines, each of which can connect to different services or local models.
Arch Linux users can install openwhispr-bin via AUR; OpenWhispr also provides a Debian .deb package, a Fedora RPM, a tar.gz, and an AppImage.
The free version of OpenWhispr cannot conveniently connect to MCP servers or external APIs; that integration capability is restricted to the paid cloud subscription tier.
OpenWhispr is an open-source, free, cross-platform (Mac, Windows, Linux) system-level voice dictation tool.
OpenWhispr has poor support in Wayland environments; basic dictation works out of the box, but assistant mode and hotkeys barely function properly.
6 more timeline events
All Facts (15)
OpenWhispr is an iOS app released on Product Hunt, whose core selling points are being 100% open source, free, and completing transcription entirely on-device.
50%UnverifiedOpenWhispr completes transcription locally, audio does not need to be uploaded to any server, there is no usage limit, and no account registration or subscription payment is required.
50%UnverifiedIf OpenWhispr uses a permissive license, the barrier for community forks is lower, but it also means others can package it into a closed-source product; if it uses a copyleft license, it can ensure improvements are contributed back to the community, but it will restrict the ways of commercial integration.
50%UnverifiedAs of the time of inclusion, OpenWhispr has 84 votes and 4 comments on Product Hunt, ranking 14th.
50%UnverifiedOpenWhispr's AI assistant mode can use selected text as context to perform instructed transformations, such as converting text to uppercase or rewriting Python if-else code into match-case syntax.
50%UnverifiedOpenWhispr's underlying architecture separates speech recognition and language model processing into two independent pipelines, each of which can connect to different services or local models.
50%UnverifiedArch Linux users can install openwhispr-bin via AUR; OpenWhispr also provides a Debian .deb package, a Fedora RPM, a tar.gz, and an AppImage.
50%UnverifiedOpenWhispr is an open-source, free, cross-platform (Mac, Windows, Linux) system-level voice dictation tool.
50%UnverifiedOpenWhispr is licensed under MIT, so users can fork the source code and add MCP and API integrations themselves.
50%UnverifiedOpenWhispr has poor support in Wayland environments; basic dictation works out of the box, but assistant mode and hotkeys barely function properly.
50%UnverifiedThe author recommends that users of Wayland compositors such as Hyprland use a community fork rather than the official version.
50%UnverifiedThe free version of OpenWhispr cannot conveniently connect to MCP servers or external APIs; that integration capability is restricted to the paid cloud subscription tier.
50%UnverifiedOpenWhispr can be invoked in any text-input context, including browsers, spreadsheets, Obsidian notes, and LinkedIn drafts.
50%UnverifiedOpenWhispr's pure dictation mode is triggered by the Super V shortcut, and the AI assistant mode is triggered by the Super Shift V shortcut.
50%UnverifiedOpenWhispr's dictation mode uses a large language model to intelligently polish transcribed content, for example automatically organizing it into a bulleted list and removing verbal filler expressions.
50%