nerd-dictation
A single-file Python script for offline speech-to-text dictation on Linux, using the VOSK speech recognition engine.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
About nerd-dictation
nerd-dictation types what you say into any application on a Linux desktop, without sending audio to a server. It uses the VOSK-API for recognition and is not tied to a particular desktop environment.
The whole tool is a single Python script meant to be read and changed, and it can be customised with your own text processing. Notes in the repository cover use with sox for audio input and ydotool for Wayland input.
Strengths
- Fully offline recognition
- Works in any application and desktop environment
- Small, hackable single script
Limitations
- Linux only
- Command-line setup with no graphical interface
- Accuracy depends on the VOSK model you download
Details
- Pricing
- FreeFree and open source.
- License
- Open source, license not stated
- Developer
- ideasman42
- Platforms
- Linux, Command line
- How it runs
- Downloadable app
- Account
- Not required
- Works offline
- Yes
- Best suited for
- Linux users who want private, offline dictation they can script
- Categories
- Local AI tools, AI voice
- Last verified
- Added
Alternatives to nerd-dictation
Compare allSoftware that can replace nerd-dictation for an important use case, and what changes if you switch.
Handy
Dictate into desktop text fields with local speech recognition.
Handy is a free MIT-licensed dictation tool for Windows, macOS and Linux that types into text fields with local recognition and a keyboard shortcut, instead of a script.
Speech Note
A Linux app for offline speech-to-text, text-to-speech and machine translation using local models.
Speech Note is a free MPL-2.0 Linux app with a graphical interface and offline engines such as Whisper, adding read-aloud and translation to dictation.
Spokenly
A dictation app for Mac, Windows, Linux and iPhone that uses local Whisper or cloud models.
Spokenly is a free, not open source dictation app for Mac, Windows, Linux and iPhone with local Whisper models or optional cloud models that send audio off the device.
Voice In
A browser extension for Chrome and Edge that types what you say into any website.
Voice In is a free Chrome and Edge extension that dictates into websites, so it works only in the browser and not in desktop applications.
nerd-dictation as an alternative
Listings that name nerd-dictation as an alternative.
Superwhisper
A voice dictation app that turns speech into text in any app, using offline or cloud recognition.
nerd-dictation is an open-source offline dictation script for Linux using VOSK, set up from the command line with no graphical interface.
Willow
An AI dictation app that turns speech into edited text in any app on Mac, Windows and iPhone.
nerd-dictation is a free Linux-only script using VOSK for offline dictation, with command-line setup and no graphical interface.
Wispr Flow
A voice dictation app that turns speech into cleaned-up text in any application.
nerd-dictation is a free, offline Linux-only dictation script built on VOSK, configured from the command line without a graphical interface.
Similar software
Related functionality, not necessarily a direct replacement.
whisper.cpp
C/C++ port of OpenAI's Whisper for fast offline speech-to-text on your own hardware.
Whisper
An open-source speech recognition model from OpenAI for transcribing and translating audio on your own machine.
Aqua Voice
An AI voice dictation app that turns speech into cleaned-up text in any app.
VoiceInk
A native macOS dictation app that transcribes speech to text offline with local AI models.
Buzz
Turn speech recordings into text with a desktop transcription app.
Speechnotes
A browser-based dictation notepad and automatic transcription service for audio and video files.
