Manual Start here
Introduction
Neato Echo is local voice dictation and meeting notes with summaries, all on your Windows PC.
Neato Echo turns your voice into text and notes on your Windows PC. Press a hotkey and speak, and your words are typed wherever your cursor is. Record a meeting and get a transcript with speaker labels and a summary. Everything is transcribed by speech models that run on your own machine, and everything you make is kept in a notes database on your PC.
Neato Echo is made by Neato Ventures in Houston, TX. It is a fork of the open-source OpenWhispr project (MIT license).
What you can do
Quickstart
Install, download the models, and dictate your first sentence.
Dictation
Press Ctrl+Win, speak, and your words appear at your cursor. Works in any app.
Meeting transcription
Record Zoom, Teams, or Google Meet calls with speaker labels, then summarize them.
Notes
Every dictation, meeting, and upload is a note you can organize, search, and export.
Local models
The speech and language models Neato Echo runs on your PC, and how to choose between them.
Common problems
Find the fix, starting from what's going wrong.
How your audio is processed
Neato Echo is local by default. Speech recognition runs on NVIDIA Parakeet, and summaries, cleanup, and the agent run on a Qwen language model, both downloaded to your PC during setup. Nothing leaves your machine unless you choose to add your own API key under Cloud Providers in Settings. See cloud vs local.
Requirements
Neato Echo runs on Windows 10 and 11, 64-bit. Download it from echo.neatoventures.com. System requirements has the detail, including what the on-device models need.
Getting help
Email [email protected], or see Getting help for what to include.
Still need help?
Write to [email protected] with your Windows version, your Neato Echo version (Settings → System), and what you were doing. A person reads every message.