Skip to content

Manual Voice and chat agent

AI agent

Speak an instruction instead of text, or open a chat that can work with your notes.

Neato Echo has an AI agent you reach two different ways, depending on what you want:

  • The voice agent types the result of an instruction at your cursor. Say "write a short thank-you note" and the note appears.
  • The chat agent opens a conversation window that can search your notes, write and edit them, read your connected calendars, and search the web if you've added a cloud provider key.

They share settings but behave quite differently.

Two ways to reach the voice agent

This is the part that surprises people. The voice agent runs when either:

  1. You press the Voice Agent Hotkey, or
  2. You say the agent's name at the start of an ordinary dictation.

The second is on by default, and the default name is Assistant, so it's possible to trigger the agent without meaning to. Your agent's name covers how the detection works and how to rename or disable it.

Where the settings live

Everything except the hotkeys is under SettingsLanguage Models under AI Models:

TabControls
Voice AgentEnable it, name it, choose its model and prompt
ChatThe chat agent's model and system prompt

The hotkeys themselves are under SettingsHotkeys under App. Voice Agent Hotkey and Chat Agent Hotkey are separate entries, and both are unset until you choose them.

Where it runs

By default both agents run on the local language model you downloaded during setup (Qwen 3.5 4B is the recommended one; smaller Qwen sizes are available in Settings → Language Models for lower-end PCs). Everything stays on your machine.

If you'd rather use a hosted model, add your own API key under Cloud Providers in Settings (OpenAI, Anthropic, Gemini, Groq and others) and choose it for the agent. See cloud vs local.

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.