# OpenWhispr

Free, open-source voice dictation with local or cloud models, meeting transcription, notes, and AI agents.

HTML: https://softbests.com/software/openwhispr
Markdown: https://softbests.com/software/openwhispr.md
Website: https://openwhispr.com

- Category: [Voice input](https://softbests.com/category/voice-input)
- Pricing: Open source
- Platforms: macOS, Windows, Linux, iOS
- Underrated

## Best for

People who want WisprFlow-style dictation without sending every recording to a closed service.

## Why it deserves attention

OpenWhispr puts a hotkey dictation box on macOS, Windows, Linux, and iOS: speak and the text lands at your cursor. You can run models such as Whisper, NVIDIA Parakeet, and Cohere entirely offline, or switch to cloud processing for speed with your own keys. It adds meeting transcription, searchable notes, and agent actions on top, with no telemetry. It is MIT-licensed, free, and has more than 10,000 GitHub stars with daily commits; local models need a capable machine and some setup, and Intel Macs miss speaker identification.

## Can replace

- [Wispr Flow](https://softbests.com/software/wispr-flow)
- [Granola](https://softbests.com/software/granola)

## Related and alternatives

- [MacWhisper](https://softbests.com/software/macwhisper)
- [VoiceInk](https://softbests.com/software/voiceink)