OpenWhispr

OpenWhispr: Open-source dictation software can dictate, transcribe, and capture meeting notes with fast, accurate AI speech-to-text.

OpenWhispr is an open-source dictation software designed to help you write faster in every application using voice input. It features local speech-to-text processing using models like Whisper and Parakeet, as well as cloud transcription options. Users can dictate text, clean up phrasing, give instructions by voice, and capture meeting notes across 100+ languages with auto-detection. It learns your custom words, medical, legal, and technical terms from your corrections. The software operates with a privacy-first design, ensuring local dictation happens entirely on your machine. It supports bring-your-own API keys and integrates with apps like ChatGPT, Claude, Cursor, Slack, and Docs.

OpenWhispr at a glance

Best for: Writer, Software engineer, Founder
Runs on: macOS, Windows, Linux, iOS, Web
Pricing: Free plan; Pro $80/user billed annually; Business $160/user billed annually; Enterprise custom pricing
Released: June 2025
Category: AI audio tool
Website: openwhispr.com

Key features

Dictate text in any application
Run local AI speech-to-text models
Bring your own API keys
Clean up and edit text by voice
Auto-learn custom words and terms
Support 100+ languages
Work completely offline

Use it for

Dictating messages and documents in desktop apps
Transcribing meeting notes and action items
Drafting emails and code chat prompts by voice
Running secure offline transcriptions while traveling

Companions

Tools that articles about OpenWhispr recommend using with it, each with its job.

Claude Code — Plugin pings you when Claude Code needs input so you can answer by voice.
Cursor — The original vibe-coding setup: talking to Cursor's Composer.
Codex — Same hands-free plugin loop for Codex.
OpenCode — Plugin support for OpenCode sessions.
Ollama — Local model to query your on-device transcript history.

Alternatives to OpenWhispr

ZWhispr — It runs multiple transcription models simultaneously for fewer mistakes.
Superwhisper — Transcribes speech offline and online with custom AI modes and templates.
OpenSuperWhisper — Provides real-time transcription using customizable keyboard shortcuts and multiple engines.
Tuxwhisper — Runs locally without cloud processing and types directly into any application.
Whishper — Transcribe and edit subtitles 100% locally with an integrated web UI.
OpenLess — Keeps data local and allows the use of your own preferred ASR and LLM providers.
Wispr Flow — It transcribes natural speech into clean, formatted text 4x faster than typing.
BetterWispr — Local models and open source design keep your speech private on your Mac.
SpeechFast — Dictate anywhere on Mac with 100 percent local processing and no cloud servers.
SpeakoFlow — Free and open source voice dictation and AI assistant that runs locally.
Openbroca — AI cleanup and translation turn messy speech into ready-to-send text directly in your apps.
Scriberr — Transcribes audio locally with AI models while keeping your data private.

All OpenWhispr alternatives