DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to dictate into any app with private, offline speech-to-text with Openwhispr

Install OpenWhispr, pick a local model and dictate anywhere with a global hotkey.

Short answer: Download the app for your platform, or on macOS run brew install --cask openwhispr; then choose a local speech-to-text model such as Whisper or NVIDIA Parakeet; set your global dictation hotkey. All steps.

Who it is forA writer or developer who types all day and wants voice input that never leaves the machine.

The problemPopular dictation apps are subscriptions that send your audio to the cloud.

The outcomeYour speech pasted at the cursor in any app, transcribed locally with no telemetry.

What you need first

  • macOS, Windows or Linux
  • Optional: local models download for offline use, or cloud provider keys
  • To run from source: Node.js 24+

Steps

  1. Download the app for your platform, or on macOS run brew install --cask openwhispr
  2. Choose a local speech-to-text model such as Whisper or NVIDIA Parakeet
  3. Set your global dictation hotkey
  4. Press the hotkey, speak, and the text appears at your cursor
  5. Use the dictation translation hotkey to speak in one language and paste in another

Prompt for your agent

Help me set up OpenWhispr/openwhispr for offline dictation on <OS>: recommend a local model for my hardware, set a hotkey, and give me a quick test routine to compare accuracy with a cloud model.

Caveat.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for OpenWhispr/openwhispr and "Dictate into any app with private, offline speech-to-text"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer