Buzz Hermes Agent — Voice Mode Setup Guide

Buzz: Use Hermes with the AI Voice Chat App

Voice mode is here, and it’s a game-changer for how you interact with Hermes. Instead of typing every command, you can now talk to your agent naturally — whether you’re coding, researching, or just walking around with ideas bouncing in your head.

This guide walks you through everything you need to get voice working, from the simplest setup to full Discord voice channel conversations. Let’s dive in.

What Voice Mode Is Good For

Voice mode shines when you want to:

• Keep your hands free while working in the terminal
• Get spoken responses in Telegram or Discord
• Have Hermes sit in a Discord voice channel for live back-and-forth
• Capture ideas quickly while walking around instead of typing

Think of it as your hands-free copilot. Debugging, brainstorming, or just asking quick questions — voice mode keeps you in the flow.

Three Ways to Use Voice

Hermes offers three distinct voice experiences:

Mode	Best for	Platform
Interactive microphone loop	Personal hands-free use while coding	CLI
Voice replies in chat	Spoken responses alongside messaging	Telegram, Discord
Live voice channel bot	Group conversations in a VC	Discord voice channels

A smart path forward: get text working first, then enable voice replies, and finally move to Discord voice channels if you want the full experience.

Step 1: Make Sure Text Works First

Before touching voice, verify the basics:

hermes

Then ask something simple:

What tools do you have available?

If that’s not solid yet, fix text mode first. Voice builds on top of a working foundation.

Step 2: Install the Right Extras

Depending on your setup, install what you need:

CLI microphone + playback:

cd ~/.hermes/hermes-agent && uv pip install -e ".[voice]"

Messaging platforms (Telegram/Discord):

cd ~/.hermes/hermes-agent && uv pip install -e ".[messaging]"

Premium ElevenLabs TTS (optional):

cd ~/.hermes/hermes-agent && uv pip install -e ".[tts-premium]"

Local NeuTTS (optional):

python -m pip install -U neutts[all]

Everything at once:

cd ~/.hermes/hermes-agent && uv pip install -e ".[all]"

Step 3: Install System Dependencies

macOS:

brew install portaudio ffmpeg opus
brew install espeak-ng

Ubuntu / Debian:

sudo apt install portaudio19-dev ffmpeg libopus0
sudo apt install espeak-ng

Here’s why each matters:

• portaudio → microphone input and playback
• ffmpeg → audio conversion for TTS and messaging
• opus → Discord voice codec support
• espeak-ng → phonemizer for NeuTTS

Step 4: Choose Your Speech Providers

Hermes supports both local and cloud speech stacks. For the easiest start, use local STT with free Edge TTS.

Add this to ~/.hermes/.env:

# Cloud STT options (local needs no key)
GROQ_API_KEY=***
VOICE_TOOLS_OPENAI_KEY=***

# Premium TTS (optional)
ELEVENLABS_API_KEY=***

Speech-to-text recommendations:

• local → best default for privacy and zero cost
• groq → very fast cloud transcription
• openai → good paid fallback

Text-to-speech recommendations:

• edge → free and good enough for most
• neutts → free local/on-device TTS
• elevenlabs → best quality
• openai → good middle ground
• mistral → multilingual, native Opus

Step 5: Recommended Config

Here’s a solid conservative default:

voice:
  record_key: "ctrl+b"
  submit_mode: "direct"  # TUI: direct | draft
  max_recording_seconds: 120
  auto_tts: false
  beep_enabled: true
  silence_threshold: 200
  silence_duration: 3.0

stt:
  provider: "local"
  local:
    model: "base"

tts:
  provider: "edge"
  edge:
    voice: "en-US-AriaNeural"

In the TUI, submit_mode controls what happens after transcription:

• direct (default) submits the transcript immediately
• draft puts it in the composer so you can edit before sending

For editable voice drafts, set submit_mode: "draft".

Want local TTS instead? Switch to:

tts:
  provider: "neutts"
  neutts:
    ref_audio: ''
    ref_text: ''
    model: neuphonic/neutts-air-q4-gguf
    device: cpu

Use Case: CLI Voice Mode

Start Hermes and turn on voice:

hermes

Then inside the CLI:

/voice on

Recording flow:

1. Press Ctrl+B
2. Speak
3. Wait for silence detection to stop automatically
4. Hermes transcribes and responds
5. If TTS is on, it speaks the answer
6. The loop can auto-restart for continuous use

Useful commands:

/voice
/voice on
/voice off
/voice tts
/voice status

Great CLI workflows:

Walk-up debugging: Say “I keep getting a docker permission error. Help me debug it.” Then continue hands-free: “Read the last error again,” “Explain the root cause in simpler terms,” “Now give me the exact fix.”

Research and brainstorming: Perfect for walking around while thinking, dictating half-formed ideas, and asking Hermes to structure your thoughts in real time.

Accessibility: If typing is inconvenient, voice mode keeps you in the full Hermes loop without the keyboard.

Tuning CLI Behavior

If Hermes starts or stops recording too aggressively, adjust these in your config:

voice:
  silence_threshold: 200   # lower = more sensitive
  silence_duration: 3.0    # seconds of silence before stopping

Start with the defaults, then tweak based on your environment. A noisy room might need a higher threshold; a quiet one might need lower.

Voice mode is one of the fastest ways to stay productive with Hermes. Start simple, experiment with providers, and soon you’ll be talking to your agent like it’s second nature.