The full list of Hyo’s settings, found at Settings → Hyo Claude Code Agent. Most people never need to touch the advanced ones.
The Setup tab gets Claude Code installed, signed in and connected. Hyo does the work — no terminal, and a browser tab opens only to approve sign-in.
| Setting |
What it does |
| Claude Code status |
Whether Claude is installed, working and signed in. Hyo checks by actually running Claude, not by looking for a file — so “ready” really means ready. |
| Auto-detect |
Finds Claude on your machine and picks one that works, including installs through nvm or fnm, or when you have more than one. |
| Install Claude |
Installs Claude Code for you in the background. |
| Sign in to Claude |
Signs you in to your Anthropic account. A browser tab opens to approve; nothing to copy. |
| Claude Code path |
Where Claude is installed. Set automatically by Auto-detect. Only change it if you need to point at a specific install. |
| Setting |
What it does |
| Model |
The default model for new conversations. You can also change it per-conversation from the status bar. See choosing a model. |
| Effort |
The default reasoning effort for new conversations. Higher is more thorough but slower and heavier on your plan. See reasoning effort. |
| Permission mode |
How much your agent checks with you — Ask first, Accept edits, Bypass all, or Plan mode. See permission modes. |
| Auto-generate conversation titles |
On by default. Names each conversation from your first message, using a small quick model call. Turn off if you’d rather name them yourself. |
| Default agent |
Which of your own agents new conversations start with. Only appears if you’ve set up agent files. |
| Setting |
What it does |
| Voice engine |
GPT-Live for a real back-and-forth call, or ElevenLabs for the turn-taking version. See turning voice on. |
| OpenAI API key |
(GPT-Live) Your key from OpenAI. Calls are billed to it at OpenAI’s per-minute rate. On your phone it also transcribes dictation. |
| Voice |
(GPT-Live) One of twenty-two voices. Play sample lets you hear the selected one. |
| Personality |
(GPT-Live) How the voice carries itself on a call. Comes with a default; edit it freely. |
| ElevenLabs API key |
(ElevenLabs) Your key from ElevenLabs. |
| Voice |
(ElevenLabs) Which voice reads replies aloud, chosen from your ElevenLabs library. |
| Playback speed |
(ElevenLabs) How fast replies are read, 1× to 2×. Starts at 1.25×. |
| Auto-speak responses |
(ElevenLabs) On by default. Reads replies aloud automatically in voice mode. |
| Setting |
What it does |
| Working directory |
The folder your agent works from. Blank means your current vault, which is right for most people. Set a path to point it elsewhere. See setting up your workspace. |
| Max output tokens |
A cap on how long a single reply can be. Default 64000 suits most models; drop to 32000 if you’re using Opus models. |
| Custom models |
Any models you’ve added by ID from the picker. Appears once you’ve added at least one, and lets you remove them. |
