agentvibes
Advanced tools
Now your AI Agents can finally talk back! Professional TTS voice for Claude Code, Claude Desktop (via MCP), and Clawdbot with multi-provider support.
Finally! Your agents can talk back!
Professional text-to-speech for Claude Code, GitHub Copilot, OpenAI Codex, Claude Desktop, and OpenClaw. Using popular open-source TTS engines: Soprano (Neural), Piper TTS (Free!), macOS Say (Built-in!), or Windows SAPI (Zero Setup!)
Author: Paul Preibisch (@997Fire) | Version: v5.2.0
| I want to... | Go here |
|---|---|
Install AgentVibes (just npx, no git!) | Quick Start Guide |
| Play agent audio using your phone as remote speakers | Android/Termux Setup |
| Secure OpenClaw on Remote Server | Security Hardening Guide ⚠️ |
| Understand what I need | Prerequisites |
| Set up on Windows (Native) | Windows Native Setup |
| Set up on Windows (Claude Desktop/WSL) | Windows WSL Guide |
| Use with GitHub Copilot | Copilot Integration |
| Use with OpenAI Codex | Codex Integration |
| Use with OpenClaw | OpenClaw Integration |
| Use natural language | MCP Setup |
| Switch voices | Voice Library |
| Configure BMAD Party Mode (agents with unique voices) | BMAD Plugin & Party Mode |
| Fix issues (git-lfs? MCP tokens? Read this!) | Troubleshooting & FAQ |
AgentVibes adds lively voice narration to your AI coding sessions!
Whether you're using Claude Code, GitHub Copilot, OpenAI Codex, Claude Desktop, or OpenClaw — AgentVibes brings AI to life with professional voices and personalities.
/agent-vibes:verbosity caveman.+ to thumbs up, - to thumbs down in any voice list. Replaces star favorites.ssh-remote and agentvibes-receiver are now first-class providers.:: format, cross-platform base64, no backslash injection.installCopilotMcp now writes both .vscode/mcp.json (Copilot Chat) AND ~/.copilot/mcp-config.json (Copilot CLI — different product, different config path)..mcp.json no longer sets AGENTVIBES_LLM. Claude Code is auto-detected via CLAUDECODE=1 env var. Copilot CLI reads its own global config. No more client config conflicts.play-tts.ps1 process blocks the playback queue, the next caller auto-kills it (no manual taskkill needed). 25-second watchdog guarantees forward progress.play-tts.ps1 captures the exact synth output filename from provider stdout instead of guessing "most recent tts-*.wav". Silent replay of old audio is gone.VoiceOverride — LLMs echo back get_config results on every call, which was overriding per-LLM routing. Fixed.lessac-medium → lessac-high default for codex — Silent synthesis failure workaround..mcp.json is now auto-migrated — v5.1.2's installer detected an existing .mcp.json and printed instructions instead of fixing it, leaving v5.1.0/v5.1.1 users still broken after upgrade. v5.1.3 merges the AGENTVIBES_LLM env var into existing configs in-place.AGENTVIBES_LLM is now validated in both mcp-server/server.py (Python regex) and play-tts.ps1 (PowerShell regex), matching play-tts.sh's ^[a-zA-Z0-9_-]+$ check. Cross-platform contract is now symmetric.npm pack content guard hardened: hard-fails (not silent-passes) when npm pack errors; uses git status --porcelain to catch UNTRACKED publishable files (the v5.1.0 disaster also could've happened with a stray new file); has explicit 60s timeout to prevent CI hangs.AGENTVIBES_LLM env var instead of hardcoding copilot — Codex / Copilot / Claude Code each get routed to their own per-LLM voice / pretext / music / effects config from audio-effects.cfg..codex/config.toml, .vscode/mcp.json, and .mcp.json all include AGENTVIBES_LLM for the right provider.npm pack content guard that fails the test suite if the working tree has uncommitted changes (the v5.1.0 disaster guard).If you already have AgentVibes installed, re-run the per-provider configure step or add "env": { "AGENTVIBES_LLM": "<your-llm>" } manually to your MCP config.
play-tts.ps1 -llm parameter restored — npm-published v5.1.0 shipped a regressed copy without -llm support, breaking the Setup tab Preview button and the agentvibes MCP text_to_speech tool on Windows. Fixed in v5.1.1. If you hit the error, clear your npx cache: npm cache clean --force then reinstall.a–z in any voice picker to jump to that letter. q, j, k, g, h, l reserved for nav/cancel./var → /private/var symlinkbmad-voices.mdThe Settings TUI now flows the way you'd expect. Down moves top-to-bottom through header → sub-tabs → content → footer. Left/Right switches sub-tabs and moves between footer buttons. Up from content returns to the active sub-tab — not always Voice. The Language tab has a proper scrollable list. Readme falls back to the AgentVibes package README when no local one exists. Escape from the installer no longer gets stuck.
.gitattributes — enforces LF for shell scripts/JS/JSON/markdown, CRLF for PowerShell; stops bin/ files showing as modified on WindowsSkip this UI? (dim) + npx agentvibes install --non-interactive (brighter), matching the [piper] [en_US-ryan-high] footer aestheticmktemp fixed — 12 calls now use BSD-compatible syntax (XXXXXX at end, then rename to add extension)bmad-party-speak.ps1 was extracting the trailing number from the speaker display name suffix (e.g. 14 from Yara-14) and passing it as the Piper --speaker index. That number is a human-readable disambiguator, not the model index — Yara-14 is actually speaker 860. Fixed to look up the full name in speaker_id_map from the .onnx.json file, matching what play-tts-piper.ps1 already did. Every configured agent was silently playing a different voice.bmad-speak.ps1 per agentHolly-7 is speaker 322, not 7parseMultiSpeaker fallback — works on fresh installs before .onnx.json is patchednormalize=0 added to ffmpeg amix — prevents voices being silenced to 50% when mixed with background musicvolume=1.5 applied to every TTS stream — agents are now loud and clearadelay=1000) — less dead air before each agent speaks►█) highlights the focused button — reuses the shared attachBtnBlink utilityinferGender now strips the numeric suffix from LibriTTS speaker names (e.g. anna-9 → anna) before looking up genderGENDER_MAP with 60+ first names covering all bundled voiceslibritts blanket-male override removed — LibriTTS voices are now inferred per-namecyan/white — no more invisible-on-dark-background instructionsEvery agent now speaks automatically in any BMAD project — no manual hook configuration needed:
bmad-party-speak.sh (Linux/macOS/WSL) or bmad-party-speak.ps1 (Windows) to ~/.claude/hooks/PostToolUse hook registered in ~/.claude/settings.json automaticallynpx agentvibes update keeps the scripts fresh across all platformsAll volume defaults lowered from 70% to 20% — new installs and agents start at a sensible level. bmad-speak scripts now inherit the global volume setting instead of ignoring it.
Pressing ← on the completion screen no longer jumps back to the installation step.
Every screen, button, and label in npx agentvibes is now fully translated:
src/i18n/en.js, es.js, fr.js, ...) with English fallbackrandomUUID() replaces Date.now() in all temp filenames (JS + PowerShell)spawnSync replaces execSync(..., { shell: true }) for which lookupsdetectMp3Player() replaces hardcoded ffplay on WindowsisWindowsTerminal now returns true/false, not the WT_SESSION UUID stringBMAD (Build More Architect Dreams) is an AI multi-agent framework where specialized agents — Architect, PM, Developer, QA, and Analyst — collaborate to build software. With this release, every agent in a BMAD party mode session now speaks aloud with their own unique voice, personality, and music on Windows — making each role instantly recognizable.
bmad-speak.js — cross-platform entry point; auto-routes to PowerShell on Windows or bash on Mac/Linuxbmad-speak.ps1 — native Windows BMAD speak with per-agent personality routingAll MCP tools now work natively on Windows. Previously 12 tools silently failed due to missing scripts:
piper and sapi on all platforms (no more windows-piper/windows-sapi)"NUL" fileAGENTVIBES_NO_PLAY env var properly cleaned up on error pathsPIPER_SPEAKER env var no longer leaks between voice switches.claude (not always global)$50 (USD) no longer becomes 50 USDThe BMad Method (Build More Architect Dreams) is an AI-driven development framework that helps you build software from ideation through agentic implementation with specialized AI agents, guided workflows, and intelligent planning that adapts to your project's complexity.
Every BMAD agent now speaks with their own unique voice, music, and personality.
When party mode runs a multi-agent discussion, the Architect, PM, Developer, QA, and Analyst each sound completely different — making every role immediately recognizable.
Auto-enabled — if BMAD is installed, party mode activates automatically. Open the BMad Tab to configure each agent:
npx agentvibes # Press B to open the BMad Tab
Per-agent configuration:
The npx agentvibes TUI now includes a full BMad Tab for managing every agent visually — inspired by the Voices tab, with the same columns and navigation polish:
npx agentvibes # Press B for BMad Tab
| Agent | Voice | Gender | Provider | Reverb | Music | Vol | Pretext |
|---|---|---|---|---|---|---|---|
| 🏢 Winston | Rose Ibex | Female | Piper (LibriTTS) | studio | jazz | 65% | Winston says |
| 🧠 Larry | Kusal | Male | Piper | hall | cinematic | 80% | Larry says |
Highlights:
16Speakers::Rose_Ibex shows as Rose Ibex; en_US-kusal-medium shows as Kusal[Space] Preview [Enter] Configure on the row itself⠋⠙⠹⠸ braille spinner while audio plays| Key | Action |
|---|---|
↑↓ / jk | Navigate agents |
Space | Preview agent (spinner shows while playing) |
Enter | Configure voice, music, volume, reverb, personality, pretext |
A | Auto-assign unique voices (gender-aware, no repeats) |
B | Bulk Edit — set music / volume / pretext / reverb for all agents |
X | Reset agent to defaults |
Run Claude on a cloud box and hear the TTS on your local machine.
The new Receiver Tab streams TTS audio from voiceless remote servers to your local machine over TCP — perfect for AWS/GCP dev boxes, WSL2, and SSH sessions.
# On your local machine — open TUI, go to Receiver tab, click Start
npx agentvibes
# On the remote server — AgentVibes auto-detects the receiver and streams
Zero-config forwarding. Works with Piper, macOS Say, and Soprano.
Full color in the TTS banner (gold voice, cyan reverb, traffic-light cache). Hide it without muting:
touch ~/.agentvibes/banner-disabled # or say "turn off the TTS banner"
Add custom prefixes to every TTS announcement!
Configure via the AgentVibes TUI Settings tab:
npx agentvibes # Navigate to Settings tab
Transform generic AI responses into your personal brand:
Before:
"Starting analysis of the codebase..."
After (with "FireBot: " intro text):
"FireBot: Starting analysis of the codebase..."
Perfect for:
Features:
Examples:
"JARVIS: " - Iron Man style"🤖 Assistant: " - With emoji"CodeBot: " - Development assistant"Chef AI: " - Cooking helperConfigure via: npx agentvibes → Settings tab
Upload your own background music with battle-tested security!
Configure via the AgentVibes TUI Music tab:
npx agentvibes # Navigate to Music tab
Replace the default background tracks with your own audio files.
Supported Formats:
Security First:
Smart Validation:
Perfect for:
Features:
Menu Options:
Configure via: npx agentvibes → Music tab
Security Certified: See full audit report at docs/security/SECURITY-AUDIT.md
🌟 v4.2 — BMAD Party Mode & SSH Receiver:
~/.agentvibes/banner-disabled)🌟 NEW IN v3.6.0 — Voice Explorer Release:
🪟 NEW IN v3.5.5 — Native Windows Support:
npx agentvibes install or .\setup-windows.ps1⚡ v3.4.0 Highlights:
⚡ Core Features:
npx agentvibes install or .\setup-windows.ps1 without Node.js)🎭 Personalization:
🚀 Integrations & Power Features:
AgentVibes' Piper TTS uses 100% Hugging Face-trained AI voice models from rhasspy/piper-voices.
What are Hugging Face voice models?
Hugging Face voice models are pre-trained artificial intelligence models hosted on the Hugging Face Model Hub platform, designed to convert text into human-like speech (Text-to-Speech or TTS) or perform other speech tasks like voice cloning and speech-to-speech translation. They're accessible via their Transformers library for easy use in applications like voice assistants, audio generation, and more.
Key Benefits:
All 50+ Piper voices AgentVibes provides are sourced from Hugging Face's open-source AI voice models, ensuring high-quality, natural-sounding speech synthesis across all supported platforms.
For Claude Desktop - Windows/WSL setup, Python requirements
For Claude Code - Project-specific setup
Agent pretexts now spoken in party mode, markdown stripped before TTS, Windows session-start hook fixed to inject context reliably, and PreToolUse hook no longer errors on grep commands.
bmad-party-speak.ps1 was extracting the trailing number from the display name suffix (e.g. 14 from Yara-14) as the Piper speaker index — wrong. Fixed to look up the full speaker name in speaker_id_map from the .onnx.json file.mktemp with extension suffix (e.g. tts-XXXXXX.wav) silently fails on BSD mktemp. Fixed all 12 occurrences across the TTS pipeline scripts./var/folders/... resolved to /private/var/folders/... in test assertions.The BMad Method (Build More Architect Dreams) is an AI-driven development framework module that helps you build software from ideation through agentic implementation with specialized AI agents, guided workflows, and intelligent planning.
Every agent in a BMAD discussion now speaks with their own individually configured voice, music, reverb, and personality — making the Architect, PM, Developer, QA, and Analyst immediately recognizable the moment they speak.
Auto-enabled — party mode activates automatically when BMAD is detected. Configure agents visually:
npx agentvibes # Press B for BMad Tab
Each agent gets:
Manage every agent from an interactive table — same polish as the Voices tab:
| Key | Action |
|---|---|
Space | Preview agent with full profile (animated spinner while playing) |
Enter | Configure voice, music, volume, reverb, personality, pretext |
A | Auto-assign unique voices (gender-aware, no repeats) |
B | Bulk Edit — set music / volume / pretext / reverb for all agents |
X | Reset agent to defaults |
The table shows Voice, Gender, Provider, Reverb, Music, Vol, Pretext columns. Voice names are automatically beautified: 16Speakers::Rose_Ibex → Rose Ibex.
Stream TTS from a cloud box, WSL2, or any voiceless server directly to your local machine over TCP:
# Local: open TUI → Receiver tab → Start
npx agentvibes
# Remote: AgentVibes auto-detects the receiver and streams audio to you
inotifywait queue worker — no polling delayFull color in the TTS banner. Silence it without muting audio:
touch ~/.agentvibes/banner-disabled # or: "turn off the TTS banner" via MCP
npx agentvibes install
💡 Tip: If npx agentvibes shows an older version: npm cache clean --force && npx agentvibes@latest
🐛 Found a bug? GitHub Issues
→ View Complete Release Notes | → View Previous Release (v4.0.1) | → View All Releases
Agent Vibes was originally created to give the Claude Code assistant a voice! Simply install it with an npx command in your terminal, and Claude Code can talk back to you.
We've now enhanced this capability by adding an MCP (Model Context Protocol) server. This integration exposes Agent Vibes' functionality directly to your AI assistant, allowing you to configure and control Agent Vibes using natural language instead of typing "/" slash commands.
Setting it up is straightforward: just add the MCP server to your Claude Code configuration files.
But the convenience doesn't stop there. With the MCP server in place, Claude Desktop can now use Agent Vibes too!
We're thrilled about this expansion because it means Claude Desktop can finally talk back as well!
If you decide to use the MCP server on Claude Desktop, after configuration, give Claude Desktop this command: "every time i give you a command, speak the acknowledgement using agentvibes and the confirmation about what you completed, when done"—and watch the magic happen!
🎯 Control AgentVibes with natural language - no slash commands to remember!
Just say "Switch to Aria voice" or "Speak in Spanish" instead of typing commands.
Works in: Claude Desktop, Claude Code
→ View Complete MCP Setup Guide - Full setup for all platforms, configuration examples, available tools, and MCP vs slash commands comparison
3 Simple Steps:
npx agentvibes install
say provider (100+ voices) ✨Just code normally - AgentVibes automatically speaks task acknowledgments and completions! 🔊
AgentVibes includes a full Text User Interface (TUI) built with blessed.js for managing voices, music, settings, and installation — all from a single interactive console.
| Command | Description |
|---|---|
npx agentvibes | Smart detection — opens Settings if installed, Install if not |
npx agentvibes install | Open the Install tab directly |
npx agentvibes config | Open the Settings tab directly |
Once inside, use Tab / Shift+Tab to switch between tabs: Voices, Music, BMad, Settings, Receiver, and Install. Use [ / ] to page through voice and music catalogs.
🍎 macOS Users (One-Time Setup):
brew install bash # Required for bash 5.x features
macOS ships with bash 3.2 (from 2007). After this, everything works perfectly!
→ Full Setup Guide - Advanced options, provider switching, and detailed setup
✅ REQUIRED:
node --version✅ STRONGLY RECOMMENDED:
⭕ OPTIONAL (TTS still works without them):
❌ DEFINITELY NOT NEEDED:
| Method | Command | Use Case |
|---|---|---|
| ✅ RECOMMENDED: NPX (via npm) | npx agentvibes install | All platforms - Just want to use AgentVibes |
| 🪟 Windows PowerShell | .\setup-windows.ps1 | Windows - Standalone installer (no Node.js needed) |
| ⚠️ Git Clone | git clone ... | Developers Only - Contributing code |
Why npx? Zero git operations, no build steps, just 30 seconds to voice!
If you want to contribute to AgentVibes:
git clone https://github.com/paulpreibisch/AgentVibes.git
cd AgentVibes
npm install
npm link
Requires: Node.js 16+, Git (no git-lfs), and npm link familiarity.
Want to run Claude Code on your Android phone with professional voices?
Simply install Termux from F-Droid (NOT Google Play) and run:
pkg update && pkg upgrade
pkg install nodejs-lts
npx agentvibes install
Termux auto-detects and installs everything needed (proot-distro for compatibility, Piper TTS, audio playback).
→ Full Android/Termux Setup Guide - Detailed troubleshooting and verification steps
AgentVibes requires certain system dependencies for optimal audio processing and playback. Requirements vary by operating system and TTS provider.
| Tool | Required For | Why It's Needed |
|---|---|---|
| Node.js ≥16.0 | All platforms | Runtime for AgentVibes installer and MCP server |
| Bash ≥5.0 | macOS | Modern bash features (macOS ships with 3.2 from 2007) |
| Python 3.10+ | Piper TTS, MCP server | Runs Piper voice engine and MCP server |
| Tool | Status | Purpose | Impact if Missing |
|---|---|---|---|
| sox | Recommended | Audio effects (reverb, EQ, pitch, compression) | No audio effects, still works |
| ffmpeg | Recommended | Background music mixing, audio padding, RDP compression | No background music or RDP optimization |
# Ubuntu/Debian
sudo apt-get update
sudo apt-get install -y sox ffmpeg python3-pip pipx
# Fedora/RHEL
sudo dnf install -y sox ffmpeg python3-pip pipx
# Arch Linux
sudo pacman -S sox ffmpeg python-pip python-pipx
Audio Playback (one of the following):
paplay (PulseAudio - usually pre-installed)aplay (ALSA - fallback)mpg123 (fallback)mpv (fallback)Why these tools?
.claude/config/audio-effects.cfg (reverb, pitch shifting, EQ, compression)# Install Homebrew if not already installed
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
# Required: Modern bash
brew install bash
# Recommended: Audio processing tools
brew install sox ffmpeg pipx
Audio Playback:
afplay (built-in - always available)say (built-in - for macOS TTS provider)Why these tools?
Option A: Native Windows (Recommended)
AgentVibes now supports native Windows with three TTS providers. No WSL required!
# Interactive Node.js installer (recommended)
npx agentvibes install
# Or use the standalone PowerShell installer
.\setup-windows.ps1
Providers available natively:
pip install soprano-tts)Requirements: Node.js 16+, PowerShell 5.1+, ffmpeg (optional, for background music & reverb)
See Windows Native Setup Guide for full instructions.
Option B: WSL (Legacy)
For Claude Desktop or WSL-based workflows, follow the Windows WSL Guide.
# Install WSL from PowerShell (Administrator)
wsl --install -d Ubuntu
Then follow Linux requirements above inside WSL.
Running Claude Code on Your Android Using Termux
AgentVibes fully supports Android devices through the Termux app. This enables you to run Claude Code with professional TTS voices directly on your Android phone or tablet!
Quick Setup:
# 1. Install Termux from F-Droid (NOT Google Play - it's outdated)
# Download: https://f-droid.org/en/packages/com.termux/
# 2. Install Node.js in Termux
pkg update && pkg upgrade
pkg install nodejs-lts
# 3. Install AgentVibes (auto-detects Android and runs Termux installer)
npx agentvibes install
What Gets Installed?
The Termux installer automatically sets up:
paplay doesn't work on Android)Why Termux Instead of Standard Installation?
Android's architecture requires special handling:
/tmp directory is not accessible on Androidpaplay don't exist✅ Termux installer solves all these issues with proot-distro and Android-native audio playback!
Requirements:
Audio Playback:
termux-media-player instead of paplayVerifying Your Setup:
# Check Termux environment
echo $PREFIX # Should show /data/data/com.termux/files/usr
# Check Node.js
node --version # Should be ≥16.0
# Check if Piper is installed
which piper # Should return /data/data/com.termux/files/usr/bin/piper
# Test audio playback
termux-media-player play /path/to/audio.wav
Troubleshooting:
| Issue | Solution |
|---|---|
| "piper: not found" | Run npx agentvibes install - auto-detects Termux |
| No audio playback | Install Termux:API from F-Droid |
| Permission denied | Run termux-setup-storage to grant storage access |
| Slow installation | Use WiFi, not mobile data (~300MB download) |
Why F-Droid and Not Google Play?
Google Play's Termux version is outdated and unsupported. Always use the F-Droid version for the latest security updates and compatibility.
# Installed automatically by AgentVibes
pipx install piper-tts
/agent-vibes:provider switch macos# Check all dependencies
node --version # Should be ≥16.0
python3 --version # Should be ≥3.10
bash --version # Should be ≥5.0 (macOS users!)
sox --version # Optional but recommended
ffmpeg -version # Optional but recommended
pipx --version # Required for Piper TTS
# Check audio playback (Linux/WSL)
paplay --version || aplay --version
# Check audio playback (macOS)
which afplay # Should return /usr/bin/afplay
| Missing Tool | Impact | Workaround |
|---|---|---|
| sox | No audio effects (reverb, EQ, pitch) | TTS still works, just no effects |
| ffmpeg | No background music, no audio padding | TTS still works, audio may cut off slightly early |
| paplay/aplay | No audio playback on Linux | Install at least one audio player |
All TTS generation still works - optional tools only enhance the experience!
Piper TTS (free, works offline on Linux/WSL) or macOS Say (free, built-in on Mac) - pick one and switch anytime.
| Provider | Platform | Cost | Quality | Setup |
|---|---|---|---|---|
| macOS Say | macOS only | Free (built-in) | ⭐⭐⭐⭐ | Zero config |
| Piper | Linux/WSL/Windows | Free | ⭐⭐⭐⭐ | Auto-downloads |
| Soprano | Linux/WSL/Windows | Free | ⭐⭐⭐⭐⭐ | pip install soprano-tts |
| Windows SAPI | Windows | Free (built-in) | ⭐⭐⭐ | Zero config |
On macOS, the native say provider is automatically detected and recommended!
AgentVibes provides 50+ slash commands and natural language MCP equivalents.
Quick Examples:
# Voice control
/agent-vibes:switch Aria # Or: "Switch to Aria voice"
/agent-vibes:list # Or: "List all voices"
# Personality & sentiment
/agent-vibes:personality pirate # Or: "Set personality to pirate"
/agent-vibes:sentiment sarcastic # Or: "Apply sarcastic sentiment"
# Language & learning
/agent-vibes:set-language spanish # Or: "Speak in Spanish"
/agent-vibes:learn # Or: "Enable learning mode"
→ View Complete Command Reference - All voice, system, personality, sentiment, language, and BMAD commands with MCP equivalents
# Configure intro text — open Settings tab
npx agentvibes
# View current intro text
cat ~/.claude/config/intro-text.txt
MCP Equivalent:
"Set my intro text to 'FireBot: '"
"What's my current intro text?"
"Clear my intro text"
# Configure background music — open Music tab
npx agentvibes
MCP Equivalent:
"Configure my background music"
"Add custom background music"
"Remove custom music"
"Preview my background music"
# Switch using friendly name
/agent-vibes:switch Ryan
/agent-vibes:switch Sarah
# List all voices with friendly names
/agent-vibes:list
# Get current voice (shows friendly name if available)
/agent-vibes:whoami
MCP Equivalent:
"Switch to Ryan voice"
"Use the Sarah voice"
"List all available voices"
Control how much Claude speaks while working! 🔊
Choose from three verbosity levels:
Quick Commands:
/agent-vibes:verbosity # Show current level
/agent-vibes:verbosity high # Maximum transparency
/agent-vibes:verbosity medium # Balanced
/agent-vibes:verbosity low # Minimal (default)
MCP Equivalent:
"Set verbosity to high"
"What's my current verbosity level?"
💡 How it works: Claude uses emoji markers (💭 🤔 ✓) in its text, and AgentVibes automatically detects and speaks them based on your verbosity level. No manual TTS calls needed!
⚠️ Note: Changes take effect on next Claude Code session restart.
🎯 Learn Spanish (or 30+ languages) while you program! 🌍
Every task acknowledgment plays twice - first in English, then in your target language. Context-based learning while you code!
→ View Complete Learning Mode Guide - Full tutorial, quick start, commands, speech rate control, supported languages, and pro tips
Two ways to add personality:
pirate personality = Pirate Marshal voice + pirate speak)→ Complete Personalities Guide - All 19 personalities, create custom ones
Use the AgentVibes TUI installer (/audio-browser) to browse, sample, and install from 914 voices interactively.
All voices now have memorable names! Instead of technical IDs like en_US-libritts_r-medium-speaker-123, just use friendly names like Ryan, Joe, or Sarah.
Voice Metadata Includes:
Curated Voices (10 personalities): These hand-picked voices cover common use cases with clear characteristics.
Speaker Variations (904 voices): High-quality Piper TTS voices from the libritts-high model. Each speaker has unique vocal characteristics, accents, and tones.
AgentVibes includes professional AI voices from Piper TTS and macOS Say with multilingual support.
🎧 Try in Claude Code: /agent-vibes:preview to hear all voices
🌍 Multilingual: Use Antoni, Rachel, Domi, or Bella for automatic language detection
→ View Complete Voice Library - All voices with clickable samples, descriptions, and best use cases
Automatically switch voices when using BMAD agents!
The BMAD plugin detects when you activate a BMAD agent (e.g., /BMad:agents:pm) and automatically uses the assigned voice for that role.
Version Support: AgentVibes supports both BMAD v4 and v6-alpha installations. Version detection is automatic - just install BMAD and AgentVibes will detect and configure itself correctly!
Open the BMad tab in the AgentVibes TUI (npx agentvibes) to configure which voice each agent uses:
📸 Don't have a screenshot yet? Run
npx agentvibes, switch to the BMad tab, and take a screenshot — then save it asdocs/installation-screenshots/screenshot-bmad-party-mode.png.
BMAD uses a loosely-coupled injection system for voice integration. BMAD source files contain placeholder markers that AgentVibes replaces with speaking instructions during installation:
Before Installation (BMAD Source):
<rules>
<r>ALWAYS communicate in {communication_language}...</r>
<!-- TTS_INJECTION:agent-tts -->
<r>Stay in character until exit selected</r>
</rules>
After Installation (with AgentVibes enabled):
<rules>
<r>ALWAYS communicate in {communication_language}...</r>
- When responding to user messages, speak your responses using TTS:
Call: `.claude/hooks/bmad-speak.sh '{agent-id}' '{response-text}'`
Where {agent-id} is your agent type (pm, architect, dev, etc.)
- Auto Voice Switching: AgentVibes automatically switches to the voice
assigned for your agent role when activated
<r>Stay in character until exit selected</r>
</rules>
After Installation (with TTS disabled):
<rules>
<r>ALWAYS communicate in {communication_language}...</r>
<r>Stay in character until exit selected</r>
</rules>
This design means any TTS provider can integrate with BMAD by replacing these markers with their own instructions!
→ View Complete BMAD Documentation - All agent mappings, language support, TTS injection details, plugin management, and customization
Use AgentVibes with GitHub Copilot in VS Code — same voices, same personalities, same MCP tools!
Copilot discovers AgentVibes through two mechanisms:
.github/copilot-instructions.md — VS Code automatically reads this file and tells Copilot how to speak (acknowledge at start, summarize at end, match verbosity, stay under 150 chars).vscode/mcp.json — registers the AgentVibes MCP server so Copilot can call text_to_speech, set_voice, and other toolsStep 1: Install AgentVibes (if you haven't already)
npx agentvibes install
Step 2: Configure VS Code MCP
Open the AgentVibes console and go to the LLM tab (press L):
npx agentvibes
Select GitHub Copilot and press Enter to install. This creates .vscode/mcp.json with the AgentVibes MCP server config and copies .github/copilot-instructions.md with the TTS protocol.
You can also create .vscode/mcp.json manually in your project root:
{
"servers": {
"agentvibes": {
"type": "stdio",
"command": "npx",
"args": ["-y", "--package=agentvibes", "agentvibes-mcp-server"]
}
}
}
VS Code starts the MCP server automatically when Copilot needs it — no manual server launch required.
Step 3: Verify
Open Copilot Chat in VS Code (Ctrl+Shift+I) and ask it to do something. You should hear an acknowledgment when Copilot starts working and a summary when it finishes.
Through the MCP tools, Copilot has the same voice capabilities as Claude Code:
| Tool | What it does |
|---|---|
text_to_speech | Speak text aloud |
set_voice | Switch voices (e.g., "ryan", "katherine") |
set_personality | Change personality (sarcastic, pirate, zen) |
set_speed | Adjust speech rate |
set_verbosity | Control detail level (low/medium/high) |
mute / unmute | Toggle audio |
get_config | Read current settings |
Copilot respects BMAD party mode. If .bmad-agent-context contains party-mode, each BMAD agent speaks with its own voice — the same per-agent routing that works in Claude Code.
| Feature | Claude Code | Copilot in VS Code |
|---|---|---|
| TTS Protocol | Injected via session-start hook | Read from .github/copilot-instructions.md |
| MCP config | .mcp.json (project root) | .vscode/mcp.json |
| Server lifecycle | Managed by Claude Code | Managed by VS Code (auto-start) |
| MCP tools | Same | Same |
| BMAD party mode | Supported | Supported |
Use AgentVibes TTS with OpenClaw - the revolutionary AI assistant you can access via any instant messenger!
What is OpenClaw? OpenClaw is a revolutionary AI assistant that brings Claude AI to your favorite messaging platforms - WhatsApp, Telegram, Discord, and more. No apps to install, no websites to visit - just message your AI assistant like you would a friend.
🌐 Website: https://openclaw.ai/
AgentVibes seamlessly integrates with OpenClaw, providing professional text-to-speech for AI assistants running on messaging platforms and remote servers.
⚠️ SECURITY IS NOT OPTIONAL - Running OpenClaw on a remote server exposes your infrastructure to attack vectors including SSH compromise, credential theft, and lateral movement.
👉 READ THIS FIRST: Security Hardening Guide - Required reading covering:
Do not expose your OpenClaw server to the internet without reading this guide.
AgentVibes includes a ready-to-use OpenClaw skill that enables TTS on messaging platforms. The setup involves two components:
Install AgentVibes on your OpenClaw server:
# On your remote server where OpenClaw is running
npx agentvibes install
The OpenClaw skill is automatically included in the AgentVibes npm package at .clawdbot/skill/SKILL.md.
How to activate the skill in OpenClaw:
Locate the skill - After installing AgentVibes, the skill is at:
node_modules/agentvibes/.clawdbot/skill/SKILL.md
Link to OpenClaw skills directory (if OpenClaw uses skills):
# Example - adjust path based on your OpenClaw installation
ln -s $(npm root -g)/agentvibes/.clawdbot/skill/SKILL.md ~/.openclaw/skills/agentvibes.md
OpenClaw auto-detection - Many OpenClaw setups automatically detect AgentVibes when it's installed. Check your OpenClaw logs for:
✓ AgentVibes skill detected and loaded
Manage your text-to-speech voices across multiple providers with the AgentVibes Voice Management Skill:
Voice Management Features:
Installation Confirmation: ✅ The skill is automatically included in the AgentVibes npm package at:
node_modules/agentvibes/.clawdbot/skill/SKILL.md
No extra setup needed - when you run npx agentvibes install on your OpenClaw server, the skill is ready to use!
Full Skill Documentation: → View Complete AgentVibes Skill Guide - 430+ lines covering:
Popular Voice Examples:
# Female voices
npx agentvibes speak "Hello" --voice en_US-amy-medium
npx agentvibes speak "Bonjour" --voice fr_FR-siwis-medium
# Male voices
npx agentvibes speak "Hello" --voice en_US-lessac-medium
npx agentvibes speak "Good day" --voice en_GB-alan-medium
# Add personality!
bash ~/.claude/hooks/personality-manager.sh set sarcastic
bash ~/.claude/hooks/play-tts.sh "Oh wonderful, another request"
CRITICAL: You MUST install AgentVibes on your phone (or local machine) to receive and play audio!
Without this, audio cannot be heard - the server generates TTS but needs a receiver to play it.
Install on Android Phone (Termux):
Install Termux from F-Droid (NOT Google Play):
Install Node.js in Termux:
pkg update && pkg upgrade
pkg install nodejs-lts
Install AgentVibes in Termux:
npx agentvibes install
Install Termux:API (for audio playback):
pkg install termux-apiInstall on Local Mac/Linux:
npx agentvibes install
Why is this needed?
Without AgentVibes installed on the receiving device, you'll generate audio but hear nothing!
┌─────────────────────────────────────────────────────────┐
│ 1. User messages OpenClaw via Telegram/WhatsApp │
│ "Tell me about the weather" │
└─────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────┐
│ 2. OpenClaw (Server) processes request with Claude │
│ AgentVibes skill generates TTS audio │
└─────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────┐
│ 3. Audio tunnels through SSH → PulseAudio (port 14713)│
│ Server: PULSE_SERVER=tcp:localhost:14713 │
└─────────────────────────────────────────────────────────┘
↓
┌─────────────────────────────────────────────────────────┐
│ 4. Local AgentVibes receives and plays audio │
│ Phone speakers, laptop speakers, etc. │
│ 🔊 "The weather is sunny and 72 degrees" │
└─────────────────────────────────────────────────────────┘
Architecture:
This creates a Siri-like experience - message from anywhere, hear responses on your phone! 📱🎤
# Basic TTS
npx agentvibes speak "Hello from OpenClaw"
# With different voices
npx agentvibes speak "Hello" --voice en_US-amy-medium
npx agentvibes speak "Bonjour" --voice fr_FR-siwis-medium
# List available voices
npx agentvibes voices
For programmatic control, use the TTS hook directly:
# Basic: Use default voice
bash ~/.claude/hooks/play-tts.sh "Hello from OpenClaw"
# Advanced: Override voice per message
bash ~/.claude/hooks/play-tts.sh "Welcome message" "en_US-amy-medium"
bash ~/.claude/hooks/play-tts.sh "Bonjour!" "fr_FR-siwis-medium"
bash ~/.claude/hooks/play-tts.sh "British greeting" "en_GB-alan-medium"
Parameters:
$1 - TEXT (required): Message to speak$2 - VOICE (optional): Voice name to override defaultFile: .claude/config/audio-effects.cfg
Customize audio effects, background music, and voice processing per agent or use default settings:
Format:
AGENT_NAME|SOX_EFFECTS|BACKGROUND_FILE|BACKGROUND_VOLUME
Example Configuration:
# Default - subtle background music
default||agentvibes_soft_flamenco_loop.mp3|0.30
# Custom agent with reverb + background
MyAgent|reverb 40 50 90 gain -2|agentvibes_soft_flamenco_loop.mp3|0.20
# Agent with pitch shift and EQ
Assistant|pitch -100 equalizer 3000 1q +2|agentvibes_dark_chill_step_loop.mp3|0.15
Available SOX Effects:
| Effect | Syntax | Example | Description |
|---|---|---|---|
| Reverb | reverb <reverberance> <HF-damping> <room-scale> | reverb 40 50 90 | Adds room ambiance (light: 30 40 70, heavy: 50 60 100) |
| Pitch | pitch <cents> | pitch -100 | Shift pitch (100 cents = 1 semitone, negative = lower) |
| Equalizer | equalizer <freq> <width>q <gain-dB> | equalizer 3000 1q +2 | Boost/cut frequencies (bass: 200Hz, treble: 4000Hz) |
| Gain | gain <dB> | gain -2 | Adjust volume (negative = quieter, positive = louder) |
| Compand | compand <attack,decay> <threshold:in,out> | compand 0.3,1 6:-70,-60,-20 | Dynamic range compression (makes quiet parts louder) |
Background Music Tracks:
Built-in tracks available in .claude/audio/tracks/:
agentvibes_soft_flamenco_loop.mp3 - Warm, rhythmic flamencoagentvibes_dark_chill_step_loop.mp3 - Modern chill electronicBackground Volume:
0.10 - Very subtle (10%)0.20 - Subtle (20%)0.30 - Moderate (30%, recommended default)0.40 - Noticeable (40%, party mode)Example: OpenClaw Custom Configuration
Create .claude/config/audio-effects.cfg on your OpenClaw server:
# OpenClaw assistant - warm voice with subtle reverb
OpenClaw|reverb 30 40 70 gain -1|agentvibes_soft_flamenco_loop.mp3|0.25
# Help desk agent - clear, bright voice
HelpDesk|equalizer 4000 1q +3 compand 0.2,0.5 6:-70,-60,-20|agentvibes_dark_chill_step_loop.mp3|0.15
# Default fallback
default||agentvibes_soft_flamenco_loop.mp3|0.30
How AgentVibes Applies Effects:
This allows per-message customization or consistent agent branding with unique audio signatures!
Perfect for running OpenClaw on a remote server with audio on your local machine:
Quick Setup:
echo 'export PULSE_SERVER=tcp:localhost:14713' >> ~/.bashrc
source ~/.bashrc
~/.ssh/config):Host your-server
RemoteForward 14713 localhost:14713
ssh your-server
agentvibes speak "Testing remote audio from OpenClaw"
Audio plays on your local speakers! 🔊
Receive and play TTS audio from servers that have no audio output!
AgentVibes Receiver is a lightweight audio client that runs on your phone, tablet, or personal computer, which receives TTS audio from remote voiceless servers, where your OpenClaw Personal Assistant or your Claude Code project is installed.
You have OpenClaw running on a Mac mini or remote server with no audio output:
Users message you via WhatsApp, Telegram, Discord but only get text responses:
AgentVibes Receiver transforms this:
One-time setup:
Flow diagram:
┌──────────────────────────────────────────┐
│ Your Mac mini / Server │
│ (OpenClaw + AgentVibes) │
│ • Generates TTS audio │
│ • Sends via SSH tunnel │
└──────────────────────────────────────────┘
↓ Encrypted SSH tunnel
┌──────────────────────────────────────────┐
│ Your Phone / Laptop │
│ (AgentVibes Receiver) │
│ • Receives audio stream (or text stream) │
│ • Auto-plays on device speakers │
└──────────────────────────────────────────┘
Real-world example:
📱 WhatsApp: "Tell me about quantum computing"
↓
🖥️ Mac mini: OpenClaw processes + generates TTS
↓ SSH tunnel (audio or text stream)
📱 Your phone (Agent Vibes Receiver): Plays audio 🔊
↓
You hear on your device speakers: "Quantum computing uses quantum bits..."
↓
💬 Conversation feels alive!
| Feature | Benefit |
|---|---|
| One-Time Pairing | SSH key setup, automatic reconnect |
| Real-Time Streaming | Low-latency audio playback |
| SSH Encryption | Secure audio tunnel |
| Tailscale Support | Easy VPN for remote servers |
| Voice Selection | Configure server-side voice |
| Audio Effects | Reverb, echo, pitch on server |
| Cache Tracking | Monitor audio generation |
| Multiple Servers | Connect to different OpenClaw instances |
# On your server (Mac mini, Ubuntu, AWS, etc.)
npx agentvibes install
# Selects OpenClaw option
# AgentVibes installs with SSH-Remote provider
# On your personal device (phone, laptop, tablet)
npx agentvibes receiver setup
# Pairing prompt with server SSH key
# Done!
→ View AgentVibes Receiver Setup Guide - Pairing, SSH configuration, Tailscale setup, troubleshooting
→ View OpenClaw Integration Guide - Server setup, voice configuration, audio effects, and best practices
What gets installed: Commands, hooks, personalities, and plugins in .claude/ directory.
→ View Complete Installation Structure - Full directory tree, file descriptions, and settings storage
# Switch voices
/agent-vibes:list # See all voices
/agent-vibes:switch Aria # Change voice
# Try personalities
/agent-vibes:personality pirate # Pirate voice + style
/agent-vibes:personality list # See all 19 personalities
# Speak in other languages
/agent-vibes:set-language spanish # Speak in Spanish
/agent-vibes:set-language list # See 30+ languages
# Replay audio
/agent-vibes:replay # Replay last message
💡 Tip: Using MCP? Just say "Switch to Aria voice" or "Speak in Spanish" instead of typing commands.
AgentVibes supports custom personalities and custom voices.
Quick Examples:
# Create custom personality
/agent-vibes:personality add mycustom
# Add custom Piper voice
/agent-vibes:add "My Voice" abc123xyz789
# Use in custom output styles
[Bash: .claude/hooks/play-tts.sh "Starting" "Aria"]
→ View Advanced Features Guide - Custom personalities, custom voices, and more
Running AgentVibes on a remote server? No problem!
✅ Auto-detects SSH sessions - Works with VS Code Remote SSH, regular SSH, cloud dev environments ✅ Zero configuration - Audio optimizes automatically ✅ No static/clicking - Clean playback through SSH tunnels
→ Remote Audio Setup Guide - Full PulseAudio configuration details
AgentVibes uses a cross-platform audio module (src/console/audio-env.js) that handles player detection and environment configuration for all supported platforms.
| Platform | PulseAudio Config | MP3 Players (preference order) | WAV Players (preference order) |
|---|---|---|---|
| Native Linux | System default (not overridden) | ffplay → play (sox) → mpg123 → cvlc → mpv | aplay → paplay → play → ffplay |
| WSL2 | Auto-detects /mnt/wslg/PulseServer | Same as Linux | Same as Linux |
| macOS | Not applicable | ffplay → play → mpg123 → cvlc → mpv → afplay | aplay → paplay → play → ffplay → afplay |
| Windows | Not applicable | ffplay → mpv (if installed) | ffplay → mpv → PowerShell SoundPlayer (built-in) |
spawn() instead of sh -c 'cmd1 || cmd2' chains. VLC/cvlc crashes when stderr is redirected inside shell wrappers.which and cached. No runtime fallback chains./mnt/wslg/PulseServer) is only set when the socket file actually exists. Hardcoding it on native Linux silently breaks audio output.System.Media.SoundPlayer is used as a built-in fallback when no cross-platform player is installed.Piper supports multi-speaker ONNX models (e.g., 16Speakers.onnx) that contain multiple voices in a single file. AgentVibes expands these automatically:
.onnx.json metadata file contains num_speakers and speaker_id_mapscanInstalledVoices() expands multi-speaker models into individual selectable entries (e.g., 16Speakers::Cori_Samuel)tts-piper-model.txt and tts-piper-speaker-id.txt to .claude/play-tts-piper.sh reads these files and passes --speaker <id> to the piper binaryVoice storage follows the same precedence chain in both JavaScript and shell:
PIPER_VOICES_DIR environment variable.claude/piper-voices-dir.txt (walks up directory tree)~/.claude/piper-voices-dir.txt~/.claude/piper-voicesAgentVibes includes a 914-voice catalog (voice-assignments.json) that lets users browse, preview, and install voices directly from the Voices tab:
16Speakers multi-speaker model's speaker_id_map, plus the full LibriTTS catalog from Hugging Facepiper-voice-manager.shvoiceId, displayName, gender, type (curated/libritts), and download URLpatchLibriTTSSpeakerNames() which maps speaker IDs to human-readable names from the registryThe catalog is loaded once at tab initialization by loadCatalog(). Installed voices (from disk scan) are shown with full color; catalog-only voices are dimmed until downloaded.
Background music requires an MP3-capable audio player. The installer detects missing players and offers to install ffmpeg automatically. If no player is found, the Music tab displays a clear error message.
# Install ffmpeg (recommended — provides ffplay)
# Ubuntu/Debian/WSL2:
sudo apt install ffmpeg
# macOS:
brew install ffmpeg
# Arch Linux:
sudo pacman -S ffmpeg
Common Issues:
❌ Error: "git-lfs is not installed"
AgentVibes does NOT require git-lfs. This error suggests:
Wrong installation method - Use npm, not git clone:
# ✅ CORRECT - Use this:
npx agentvibes install
# ❌ WRONG - Don't clone unless contributing:
git clone https://github.com/paulpreibisch/AgentVibes.git
Different project - You may be in a BMAD-METHOD or other repo that uses git-lfs
Global git config - Your git may have lfs enabled globally:
git config --global --list | grep lfs
Solution: Use npx agentvibes install - no git operations needed!
No Audio Playing?
ls -la .claude/hooks/session-start-tts.sh/agent-vibes:sample AriaCommands Not Found?
npx agentvibes install --yes
→ View Complete Troubleshooting Guide - Solutions for audio issues, command problems, MCP errors, voice issues, and more
Quick Update (From Claude Code):
/agent-vibes:update
Alternative Methods:
# Via npx
npx agentvibes update --yes
# Via npm (if installed globally)
npm update -g agentvibes && agentvibes update --yes
Check Version: /agent-vibes:version
→ View Complete Update Guide - All update methods, version checking, what gets updated, and troubleshooting
Quick Uninstall (Project Only):
npx agentvibes uninstall
Uninstall Options:
# Interactive uninstall (confirms before removing)
npx agentvibes uninstall
# Auto-confirm (skip confirmation prompt)
npx agentvibes uninstall --yes
# Also remove global configuration
npx agentvibes uninstall --global
# Complete uninstall including Piper TTS
npx agentvibes uninstall --global --with-piper
What Gets Removed:
Project-level (default):
.claude/commands/agent-vibes/ - Slash commands.claude/hooks/ - TTS scripts.claude/personalities/ - Personality templates.claude/output-styles/ - Output styles.claude/audio/ - Audio cache.claude/tts-*.txt - TTS configuration files.agentvibes/ - BMAD integration filesGlobal (with --global flag):
~/.claude/ - Global configuration~/.agentvibes/ - Global cachePiper TTS (with --with-piper flag):
~/piper/ - Piper TTS installationTo Reinstall:
npx agentvibes install
💡 Tips:
--global if you want to completely reset AgentVibes--with-piper if you also want to remove the Piper TTS enginenpx agentvibes status to check installation statusQ: Does AgentVibes require git-lfs?
A: NO. AgentVibes has zero git-lfs requirement. Use npx agentvibes install - no git operations needed.
Q: Do I need to clone the GitHub repository?
A: NO (unless you're contributing code). Normal users should use npx agentvibes install. Repository cloning is only for developers who want to contribute to the project.
Q: Why is the GitHub repo so large? A: The repo includes demo files and development dependencies (node_modules). The actual npm package you download is < 50MB and optimized for users.
Q: What's the difference between npm install and git clone? A:
npx agentvibes install → For users - Downloads pre-built package, zero git operations, instant setupgit clone ... → For developers only - Full source code, development setup, contributing codeQ: I saw an error about git-lfs, is something wrong? A: You're likely:
npx not git clone)AgentVibes itself does NOT use or require git-lfs.
Q: Does MCP consume tokens from my context window? A: YES. Every MCP tool schema adds to the context window. AgentVibes MCP is designed to be minimal (~1500-2000 tokens), but if you're concerned about token usage, you can use slash commands instead of MCP.
Q: What's the difference between using MCP vs slash commands? A:
/agent-vibes:switch Aria), zero token overheadBoth do the exact same thing - MCP is more convenient, slash commands are more token-efficient.
Q: Is AgentVibes just a bash script? A: No. AgentVibes includes:
Q: Can I use AgentVibes without BMAD? A: YES. AgentVibes works standalone. BMAD integration is optional - only activates if you install BMAD separately.
Q: What are the audio dependencies? A:
Q: How do I browse and install voices?
A: Use the built-in TUI installer by running /audio-browser in Claude Code. Navigate with arrow keys, press ENTER to sample voices, and select one to install. AgentVibes switches to the chosen voice automatically.
Q: What are friendly voice names?
A: Instead of technical IDs like en_US-ryan-high, you can now use simple names like "Ryan" when switching voices. All 904+ voices have friendly names matched to their characteristics.
Q: How do I set up custom intro text?
A: During installation you'll be prompted for intro text. You can also configure it anytime via npx agentvibes → Settings tab. Enter text like "FireBot: " and it will prefix all TTS announcements.
Q: Can I use my own background music?
A: Yes! Run npx agentvibes and open the Music tab. Select "Change music" and provide the path to your audio file (.mp3, .wav, .ogg, or .m4a). Files are validated for security and must be under 50MB.
Q: What's the recommended duration for custom music? A: Between 30-90 seconds is ideal for smooth looping. The system supports up to 300 seconds (5 minutes) but will warn you if the duration is non-optimal.
Q: Are friendly voice names case-sensitive? A: No! You can type "ryan", "Ryan", or "RYAN" - they all work. The voice resolution is case-insensitive.
Q: Does custom music work with all TTS providers? A: Yes! Custom background music works with Piper TTS, Soprano, macOS Say, and Windows SAPI.
Q: Can I preview music before setting it as my background?
A: Yes! In npx agentvibes → Music tab, select "Preview current" to hear your music. During installation, you can also sample all built-in tracks.
Q: What security measures protect custom music uploads? A: AgentVibes implements defense-in-depth security with 7 validation layers, tested against 180+ attack variations:
path.resolve() prevents traversal attacks (../, encoded, Unicode)Security Certification:
See full security audit: docs/security/SECURITY-AUDIT.md
Q: Has the security been independently verified?
A: Yes! AgentVibes v3.6.0 includes a comprehensive security audit with 180+ attack variations tested. All path traversal, symlink, Unicode, null byte, and edge case attacks were successfully blocked (100% rejection rate). The system is OWASP CWE-22 compliant and includes a detailed security audit report at docs/security/SECURITY-AUDIT.md.
Q: What attack patterns were tested? A: The security test suite covers:
Every attack was correctly rejected with no information disclosure.
Q: Why isn't Claude speaking? A: Common causes:
npx agentvibes install --yessox and ffmpeg/agent-vibes:sample AriaQ: Can I use this on Windows? A: Yes! AgentVibes supports native Windows with PowerShell scripts (Soprano, Piper, SAPI providers). See Windows Native Setup. WSL is also supported for legacy workflows - see Windows WSL Guide.
Q: How do I reduce token usage? A:
/agent-vibes:verbosity low)API Costs & Usage:
Third-Party Services:
Privacy & Data:
Software License:
Use at Your Own Risk:
Built with ❤️ by Paul Preibisch
Powered by:
Contributors:
Special Thanks:
If AgentVibes makes your coding more fun:
Ready to give Claude a voice? Install now and code with personality! 🎤✨
FAQs
Now your AI Agents can finally talk back! Professional TTS voice for Claude Code, Claude Desktop (via MCP), and Clawdbot with multi-provider support.
The npm package agentvibes receives a total of 2,325 weekly downloads. As such, agentvibes popularity was classified as popular.
We found that agentvibes demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
OpenAI rotated macOS signing certificates after a malicious Axios package reached its CI pipeline in a broader software supply chain attack.
Security News
Open source is under attack because of how much value it creates. It has been the foundation of every major software innovation for the last three decades. This is not the time to walk away from it.
Security News
Socket CEO Feross Aboukhadijeh breaks down how North Korea hijacked Axios and what it means for the future of software supply chain security.