Turning voice on

Voice is off by default. Turning it on is a one-time setup: you connect an ElevenLabs account and pick a voice. After that it’s ready whenever you want it.

Why ElevenLabs

Voice mode uses ElevenLabs for two things — turning your speech into text so your agent understands you, and turning its replies into a natural-sounding voice. You connect it with your own ElevenLabs key, which is why voice is separate from the rest of Hyo.

The setup

1. Get an ElevenLabs API key. Sign in at elevenlabs.io and copy your key from Settings → API Keys.
2. Paste it into Hyo. Go to Settings → Hyo Claude Code Agent → Voice, and paste your key into ElevenLabs API key.
3. Pick a voice. Once your key’s in, the Voice dropdown fills with the voices from your ElevenLabs library. Choose the one you like.

That’s it. Voice is now available.

While you’re there

Two more settings in the same place, both optional:

• Playback speed — how fast it reads replies aloud. Starts at 1.25×; you can set it from 1× up to 2×.
• Auto-speak responses — on by default, so replies are read aloud automatically in voice mode. Turn it off if you’d rather trigger playback yourself.

Turning it on in a conversation

With setup done, click the microphone in the status bar of any conversation to switch that tab into voice. The next page covers what you’ll see.

First time takes a moment

The first time you open voice mode, Hyo downloads two small models that run on your own machine — they’re what tell when you’re speaking and when you’ve finished a thought. It’s a one-time download, and after that voice opens instantly.