agentvibes 5.3.0 → 5.5.0

package/README.md

@@ -4,14 +4,14 @@
 >
 > 🌐 **[agentvibes.org](https://agentvibes.org)**
 >
-> 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!)
+> Professional text-to-speech for **Claude Code**, **Claude Desktop**, **Warp Terminal**, and **OpenClaw** - **Soprano** (Neural), **Piper TTS** (Free!), **macOS Say** (Built-in!), or **Windows SAPI** (Zero Setup!)
 
 [![npm version](https://img.shields.io/npm/v/agentvibes)](https://www.npmjs.com/package/agentvibes)
 [![Test Suite](https://github.com/paulpreibisch/AgentVibes/actions/workflows/test.yml/badge.svg)](https://github.com/paulpreibisch/AgentVibes/actions/workflows/test.yml)
 [![Publish](https://github.com/paulpreibisch/AgentVibes/actions/workflows/publish.yml/badge.svg)](https://github.com/paulpreibisch/AgentVibes/actions/workflows/publish.yml)
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 
-**Author**: Paul Preibisch ([@997Fire](https://x.com/997Fire)) | **Version**: v5.3.0
+**Author**: Paul Preibisch ([@997Fire](https://x.com/997Fire)) | **Version**: v5.5
 
 ---
 
@@ -20,17 +20,14 @@
 | I want to... | Go here |
 |--------------|---------|
 | **Install AgentVibes** (just `npx`, no git!) | [Quick Start Guide](docs/quick-start.md) |
-| **Play agent audio using your phone as remote speakers** | [Android/Termux Setup](#-android--termux) |
+| **Run Claude Code on Android** | [Android/Termux Setup](#-android--termux) |
 | **Secure OpenClaw on Remote Server** | [Security Hardening Guide](docs/security-hardening-guide.md) ⚠️ |
 | **Understand what I need** | [Prerequisites](#-prerequisites) |
 | **Set up on Windows (Native)** | [Windows Native Setup](WINDOWS-SETUP.md) |
 | **Set up on Windows (Claude Desktop/WSL)** | [Windows WSL Guide](mcp-server/WINDOWS_SETUP.md) |
-| **Use with GitHub Copilot** | [Copilot Integration](#-github-copilot-integration) |
-| **Use with OpenAI Codex** | [Codex Integration](#-openai-codex-integration) |
 | **Use with OpenClaw** | [OpenClaw Integration](#-openclaw-integration) |
 | **Use natural language** | [MCP Setup](docs/mcp-setup.md) |
 | **Switch voices** | [Voice Library](docs/voice-library.md) |
-| **Configure BMAD Party Mode** (agents with unique voices) | [BMAD Plugin & Party Mode](#-bmad-plugin) |
 | **Fix issues** (git-lfs? MCP tokens? Read this!) | [Troubleshooting](docs/troubleshooting.md) & [FAQ](#-frequently-asked-questions-faq) |
 
 ---
@@ -39,345 +36,51 @@
 
 **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.
+Whether you're coding in Claude Code, chatting in Claude Desktop, using Warp Terminal, or running OpenClaw - AgentVibes brings AI to life with professional voices and personalities.
 
 ---
 
-## 🎯 NEW IN v5.3.0 — Take Control of Remote Voices
-
-- **Customize every remote announcement individually** — pass `--voice`, `--pretext`, `--music`, `--volume`, `--effects`, `--speed`, `--provider` on the command line for just that one message. No more editing config files and changing them back.
-- **Skip the intro phrase on demand** — `--pretext ""` suppresses the pretext for a single message.
-- **Long messages and special characters work correctly on Windows** — text with quotes, apostrophes, emoji, or multi-line content no longer gets truncated on its way to the voice engine.
-- **Voice playback works on Windows servers with no monitor** — a background helper runs in your user session and picks up announcements from a queue, so audio plays even when SSH'ing in headless.
-- **Voice preview on remote servers streams to the right device** — TUI preview no longer falls back to local audio on machines without speakers.
-- **No more double intro phrases** when both sender and receiver have pretext configured.
-- **55 new tests** for BMAD party mode voice assignment and agent isolation.
-
-## 🎯 v5.2.1 — Multi-LLM Identity & Install Polish
-
-- **Copilot gets its own voice + pretext + music** — "Copilot here" with bossa nova, fully distinct from Claude Code and Codex.
-- **Per-tool MCP configs with explicit identity** — `.vscode/mcp.json`, `.codex/config.toml`, `~/.copilot/mcp-config.json` each set their own `AGENTVIBES_LLM`.
-- **`get_config` MCP tool returns detected LLM** — calling assistants can confirm their routing and respond with the right voice.
-- **Setup nav: Install → Install → Install → Configure → Configure → Configure** — keyboard flow walks all three providers' Configures before landing on Default.
-- **Claude Code default background music** set to Chillwave.
-- **Linux compatibility refinements** — CRLF, permissions, transport provider override.
-
-## 🎯 v5.2.0 — Remote Voice Preview + Caveman Mode + Voice Ratings
-
-- **Caveman verbosity mode** — Ultra-terse TTS fragments. Set via `/agent-vibes:verbosity caveman`.
-- **👍/👎 voice ratings** — Press `+` to thumbs up, `-` to thumbs down in any voice list. Replaces star favorites.
-- **Remote voice preview** — TUI voice preview works on headless servers via SSH receiver. No local audio needed.
-- **SSH receiver routing** — `ssh-remote` and `agentvibes-receiver` are now first-class providers.
-- **Voice validation hardened** — Multi-speaker `::` format, cross-platform base64, no backslash injection.
-
-## 🛡️ v5.1.4 — TTS Resilience Overhaul + Default LLM Provider
-
-- **Default LLM provider** — New fallback entry at the bottom of Setup → Providers. Config-only; opens the standard Configure modal. Used when a tool calls TTS without identifying its LLM.
-- **Per-LLM background music auto-enables** — Setting a bg track on the per-LLM Configure modal actually plays it now (no need to also toggle global bg music).
-- **Copilot CLI support** — `installCopilotMcp` now writes both `.vscode/mcp.json` (Copilot Chat) AND `~/.copilot/mcp-config.json` (Copilot CLI — different product, different config path).
-- **Per-client routing architecture** — `.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.
-- **Self-healing TTS mutex** — When a stuck `play-tts.ps1` process blocks the playback queue, the next caller auto-kills it (no manual `taskkill` needed). 25-second watchdog guarantees forward progress.
-- **No more stale audio replay** — `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.
-- **Per-LLM voice wins over explicit `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.
-- **Scratch file rename + ASCII-only encoding** — Eliminates accumulating compound audio files and CP1252 parse errors on Windows.
-- **Setup → Install confirmation** now advances focus to the next provider row (Install → Install → Install flow).
+## 🌟 NEW IN v5.5 — Per-LLM Audio Routing
 
----
-
-## 🛡️ v5.1.3 — Hardening Pass (Adversarial Review Followup)
-
-- **Existing `.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.
-
----
-
-## 🔀 v5.1.2 — MCP Per-LLM Routing Hotfix
-
-- **MCP server now reads `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`.
-- **MCP launcher templates set the env var** automatically — `.codex/config.toml`, `.vscode/mcp.json`, and `.mcp.json` all include `AGENTVIBES_LLM` for the right provider.
-- **24 new regression tests** prevent this class of bug from shipping again, including a `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.
-
----
-
-## 🩹 v5.1.1 — Windows TTS Hook Hotfix
-
-- **`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.
-
----
-
-## 🎙️ NEW IN v5.1.0 — Voice Picker Overhaul + Auto-Save Agent Modal
-
-- **Auto-save in agent modal** — Voice/personality/music/reverb/pretext changes save automatically as you edit them. Brief "✓ Saved!" toast confirms each change.
-- **Unique LibriTTS names** — 904 speakers get deterministic surnames: **Anna Bell**, **Anna Carter**, …, **Anna Quinn**. No more "Anna-2", "Anna-3" duplicates.
-- **Pink ♀ / blue ♂ gender symbols** — Colored gender indicators in the main Voices tab and all voice picker modals.
-- **First-letter quick jump** — Press `a`–`z` in any voice picker to jump to that letter. `q`, `j`, `k`, `g`, `h`, `l` reserved for nav/cancel.
-- **PgUp / PgDn / Home / End** in voice pickers
-- **3 new background music tracks** — Late Night Hip Hop Groove, Drifting Down the Hall, Midnight Charleston Stomp
-- **Search bar removed from voice pickers** — replaced by first-letter jump (faster, no focus issues)
-- **Voices tab corruption fix** — uninstalled rows no longer lose their Provider column when navigated onto
-- **Music + Voices tab blink artifacts gone**
-
----
-
-## 🚀 v5.0.0 — Multi-Provider Support: Claude Code + Copilot + Codex
-
-- **GitHub Copilot + OpenAI Codex in VS Code** — AgentVibes now supports all three major AI coding assistants. Install and configure each from the TUI.
-- **One Setup tab** — 4-step wizard (Language → Deps → TTS Engine → Providers) replaces old installer + LLM tabs. Returning users skip to Providers.
-- **Per-provider audio config** — Each LLM gets its own Voice, TTS Engine, Reverb, Music, and Pretext via Configure modal.
-- **Settings redesigned** — Clean flat list: Language, TTS Engine, Voice, Verbosity, Audio Destination, Config Storage, Re-run Wizard.
-- **Voice picker upgraded** — 3-column display, Space bar preview, scroll stays in place.
-
----
-
-## 🐛 v4.6.8 — Fresh Install Crash Fix
-
-- **Settings tab crash fixed** — no longer crashes when navigating to Settings on a fresh install with no voice configured
-- **macOS test fix** — replay path assertion handles `/var` → `/private/var` symlink
-- **BMAD pretext parsing improved** — voices pretext extracted correctly from `bmad-voices.md`
-
----
-
-## 🎙️ v4.6.7 — Party Mode TTS Fixes
-
-- **Agent pretexts now spoken in party mode** — "John, Product Manager here" was being silently dropped due to a pre-synthesis timing bug. Fixed.
-- **No more spoken asterisks** — markdown stripped before TTS in party mode
-- **Windows session start TTS fixed** — hook now outputs proper JSON so TTS activates reliably on session start
-- **PreToolUse hook no longer errors** on grep/regex commands
-
----
-
-## 🧭 v4.6.6 — Natural TUI Navigation
-
-The 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.
-
----
-
-## 🔧 NEW IN v4.6.5 — Line Endings, TUI Non-Interactive Hint, Release Process
-
-- **`.gitattributes`** — enforces `LF` for shell scripts/JS/JSON/markdown, `CRLF` for PowerShell; stops `bin/` files showing as modified on Windows
-- **TUI non-interactive hint** — installer header now shows a two-tone hint on row 2: `Skip this UI?` (dim) + `npx agentvibes install --non-interactive` (brighter), matching the `[piper] [en_US-ryan-high]` footer aesthetic
-
----
-
-## 🐛 NEW IN v4.6.4 — CI & macOS Fixes
-
-- **macOS `mktemp` fixed** — 12 calls now use BSD-compatible syntax (XXXXXX at end, then rename to add extension)
-- **CI test suite green** — macOS path symlink, execute permission, and parallel mktesk race all fixed
-
----
-
-## 🐛 NEW IN v4.6.3 — Party Mode Correct Voices
-
-- **Party mode agents speak with their configured voices** — `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.
-
----
-
-## 🐛 NEW IN v4.6.2 — Party Mode Voices, LibriTTS Speaker Fix, Agent Pretext
-
-- **Party mode agents now speak in their unique voices** — SKILL.md wired to `bmad-speak.ps1` per agent
-- **LibriTTS speaker IDs resolved correctly** — `Holly-7` is speaker 322, not 7
-- **Agent pretext spoken on Windows** — "Mary, Business Analyst here." before every response
-- **`parseMultiSpeaker` fallback** — works on fresh installs before `.onnx.json` is patched
-
----
-
-## 🌟 NEW IN v4.6.1 — Party Mode Voice Clarity + Agent Config UI Polish
-
-### 🔊 Voice Volume Fixed in Party Mode
-
-- **`normalize=0`** added to ffmpeg `amix` — prevents voices being silenced to 50% when mixed with background music
-- **Voice boost `volume=1.5`** applied to every TTS stream — agents are now loud and clear
-- **Music intro reduced to 1 second** (`adelay=1000`) — less dead air before each agent speaks
-- **Pre-synthesis gap reduction** — WAV files are generated *before* acquiring the mutex, so synthesis overlaps with the previous agent's playback (gap drops from ~4–6s to ~1s)
-
-### 🎛️ BMAD Agent Config — Preview + Split Fields
-
-- **Music Track** and **Music Vol** are now separate fields in the agent editor — each opens its own dialog
-- **Preview button** plays the selected voice with full effects: personality, reverb, background music track and volume
-- **Blinking indicator** (`►█`) highlights the focused button — reuses the shared `attachBtnBlink` utility
-- **Preview spinner** animates while audio is playing
-- **Tab→Save hint** shown in the volume input dialog
-
-### 🚻 Voice Gender Auto-Assign Fixed
-
-- `inferGender` now strips the numeric suffix from LibriTTS speaker names (e.g. `anna-9` → `anna`) before looking up gender
-- Expanded `GENDER_MAP` with 60+ first names covering all bundled voices
-- `libritts` blanket-male override removed — LibriTTS voices are now inferred per-name
-
-### 🐛 Other Fixes
-
-- Volume dialog text now uses `cyan`/`white` — no more invisible-on-dark-background instructions
-- After saving agent settings, focus correctly returns to the agent list (Enter re-opens the agent)
-- Boundary navigation in agent fields no longer jumps to buttons prematurely
-
----
-
-## 🌟 NEW IN v4.6 — Party Mode Auto-Install + Volume Fix
-
-### 🎉 BMAD Party Mode TTS — Zero Setup
-
-Every agent now speaks automatically in any BMAD project — no manual hook configuration needed:
-
-- Installer copies `bmad-party-speak.sh` (Linux/macOS/WSL) or `bmad-party-speak.ps1` (Windows) to `~/.claude/hooks/`
-- `PostToolUse` hook registered in `~/.claude/settings.json` automatically
-- `npx agentvibes update` keeps the scripts fresh across all platforms
-
-### 🔊 Background Music Volume Default: 20%
-
-All 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.
-
-### 🐛 Installer Navigation Fix
-
-Pressing ← on the completion screen no longer jumps back to the installation step.
-
-### 🧪 628 Tests, Zero Failures
-
----
-
-## 🌟 v4.5 — "Speak Every Language" Release
-
-### 🌍 Multilingual TUI — 9 Languages
-
-Every screen, button, and label in `npx agentvibes` is now fully translated:
-
-- **English, Spanish, French, German, Portuguese, Japanese, Korean, Chinese (Simplified), Italian**
-- Language selection on first launch — pick your language before anything else
-- Language sub-tab in Settings — switch live, no restart needed
-- All tab labels, buttons, footer hints, status messages, and BMAD/Receiver tabs translated
-- Per-language i18n files (`src/i18n/en.js`, `es.js`, `fr.js`, ...) with English fallback
-
-### 🪟 Windows Security Hardening
-
-- **Unpredictable temp files** — `randomUUID()` replaces `Date.now()` in all temp filenames (JS + PowerShell)
-- **No shell injection** — `spawnSync` replaces `execSync(..., { shell: true })` for `which` lookups
-- **Smart music player detection** — `detectMp3Player()` replaces hardcoded `ffplay` on Windows
-- **Boolean fix** — `isWindowsTerminal` now returns `true/false`, not the `WT_SESSION` UUID string
-
-### 🎙️ Cross-Platform BMAD Speak
-
-BMAD (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/Linux
-- `bmad-speak.ps1` — native Windows BMAD speak with per-agent personality routing
-
-### 🧪 600 Tests, Zero Failures
-
----
-
-## 🌟 v4.4 — Full Platform Parity Release
-
-### 🪟 Windows MCP Parity — 27/27 Tools Working
-
-All MCP tools now work natively on Windows. Previously 12 tools silently failed due to missing scripts:
-
-- **6 new PowerShell scripts** — personality-manager, speed-manager, language-manager, learn-manager, verbosity-manager, clean-audio-cache
-- **Unified provider naming** — `piper` and `sapi` on all platforms (no more `windows-piper`/`windows-sapi`)
-- **replay command** added to voice-manager for Windows
-- **Adversarial review** — 24 issues found, 10 fixed (3 CRITICAL, 4 HIGH, 3 MEDIUM)
-- **28 new tests** covering script parity, effects round-trip, provider management, and naming consistency
-- **Feature-platform matrix** — [docs/feature-platform-matrix.md](docs/feature-platform-matrix.md) tracks all 85 features across Linux, macOS, Windows, and WSL
-
-### Bug Fixes (HIGH)
-- ffmpeg stderr redirected to temp file instead of literal `"NUL"` file
-- `AGENTVIBES_NO_PLAY` env var properly cleaned up on error paths
-- `PIPER_SPEAKER` env var no longer leaks between voice switches
-- Provider config now uses project-local `.claude` (not always global)
-- Text sanitization relaxed — `$50 (USD)` no longer becomes `50 USD`
-
----
-
-## 🌟 v4.3 — Windows Parity + BMAD Party Mode
-
-### 🎭 BMAD Party Mode — Every Agent Has Its Own Voice
-
-The 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:
-
-```bash
-npx agentvibes   # Press B to open the BMad Tab
-```
-
-**Per-agent configuration:**
-- 🎙️ **Voice** — 914 voices to choose from, auto-assigned gender-aware
-- 🎵 **Background Music** — Unique ambient track per agent (cinematic, lo-fi, jazz...)
-- 🎚️ **Music Volume** — Per-agent level, or set all at once via Bulk Edit
-- 🎛️ **Reverb** — none / room / hall / cathedral / studio per agent
-- 💬 **Pretext** — Custom intro phrase ("Winston says:..." before every line)
-- 🎭 **Personality** — sarcastic, dramatic, pirate, cheerful, and more
-- 🔇 **No Overlap** — Speech lock ensures agents never talk over each other
-- ✨ **Markdown-Clean** — Asterisks and formatting stripped before TTS
-
-### 🎛️ BMad Tab — Visual Agent Configurator
-
-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:
-
-```bash
-npx agentvibes   # Press B for BMad Tab
-```
+Give **each LLM its own voice, pretext, and music** — Claude Code, Copilot, and Codex can all sound different without touching global settings.
 
-| 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 |
+- Add `llm:<name>|...|voice|pretext|engine` rows to `audio-effects.cfg`
+- MCP server auto-detects which LLM is calling and passes `--llm <key>`
+- Configure via **Setup → Default → Configure** in the TUI
 
-**Highlights:**
-- **Beautified voice names** — `16Speakers::Rose_Ibex` shows as `Rose Ibex`; `en_US-kusal-medium` shows as `Kusal`
-- **Gender & Provider columns** — see voice metadata at a glance, just like the Voices tab
-- **Inline row hints** — navigate to any agent and see `[Space] Preview  [Enter] Configure` on the row itself
-- **Preview spinner** — animated `⠋⠙⠹⠸` 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 |
+Also fixed: Windows installer crash (`spinner.info is not a function`) on **reinstall** with an older global AgentVibes install.
 
 ---
 
-### 🖥️ SSH Receiver — Hear Your Headless Server
+## v5.4 — TUI Installer, Spinner Fix & Dependency Cleanup
 
-**Run Claude on a cloud box and hear the TTS on your local machine.**
+### 🎤 Agent Vibes v1.0 Voice Browser
 
-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.
+**🎤 Browse, Sample & Install 914 Voices in Real-Time**
 
 ```bash
-# 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
+npx agentvibes-voice-browser
 ```
 
-Zero-config forwarding. Works with Piper, macOS Say, and Soprano.
+The new **AgentVibes Voice Browser** is an interactive console application that lets you:
 
----
+- 🎧 **Hear Before You Choose** - Real-time audio sampling with one keypress
+- ⭐ **Mark Your Favorites** - Build your personal voice collection
+- 🔍 **Smart Search** - Filter by name, personality, accent, or gender
+- 📦 **One-Click Install** - Press 'I' to instantly switch to any voice
+- 🎨 **Beautiful Interface** - Stunning terminal UI powered by blessed.js
 
-### ⚡ TTS Latency -~1 Second
+**914 Total Voices:**
+- 904 High-Quality Piper TTS Speakers (libritts-high model)
+- 10 Hand-Curated Personality Voices
 
-- **Batched Node.js calls** — 6 separate profile reads collapsed into 1 (~900ms saved)
-- **inotifywait queue** — file-event-based worker, no polling delay
-- **Background cache cleanup** — off the critical path every 10th call
-
----
-
-### 🎨 ANSI Banner Colors + Toggle
-
-Full color in the TTS banner (gold voice, cyan reverb, traffic-light cache). Hide it without muting:
+**Perfect for:**
+- Finding your ideal AI voice
+- Exploring voice characteristics
+- Quick voice switching
+- Building favorite collections
 
-```bash
-touch ~/.agentvibes/banner-disabled   # or say "turn off the TTS banner"
-```
+Launch now: `npx agentvibes-voice-browser`
 
 ---
 
@@ -385,10 +88,8 @@ 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:
-
 ```bash
-npx agentvibes   # Navigate to Settings tab
+npx agentvibes config intro-text
 ```
 
 Transform generic AI responses into your personal brand:
@@ -422,7 +123,7 @@ Transform generic AI responses into your personal brand:
 - `"CodeBot: "` - Development assistant
 - `"Chef AI: "` - Cooking helper
 
-Configure via: `npx agentvibes` → Settings tab
+Configure now: `npx agentvibes config intro-text`
 
 ---
 
@@ -430,13 +131,11 @@ Configure via: `npx agentvibes` → Settings tab
 
 **Upload your own background music with battle-tested security!**
 
-Configure via the AgentVibes TUI Music tab:
-
 ```bash
-npx agentvibes   # Navigate to Music tab
+npx agentvibes config music
 ```
 
-Replace the default background tracks with your own audio files.
+Replace the default background tracks with your own audio files for complete sonic branding.
 
 **Supported Formats:**
 - 🎵 MP3 (.mp3)
@@ -461,10 +160,10 @@ Replace the default background tracks with your own audio files.
 - Duration warnings for non-optimal lengths
 
 **Perfect for:**
-- 🎮 **Making coding fun** - Your favorite beats while you build
-- 🎼 **Setting the mood** - Match the music to the task (lo-fi for debugging, epic for shipping)
-- 🗂️ **Identifying projects** - Different track per repo so you always know which project Claude is in
-- 🎹 **Deep focus** - Ambient or classical to stay in flow
+- 🎸 **Team Audio Branding** - Company theme music
+- 🎮 **Gaming Sessions** - Epic background tracks
+- 🎼 **Personal Playlists** - Your favorite instrumental
+- 🎹 **Focus Music** - Lo-fi, classical, ambient
 
 **Features:**
 - Preview before setting
@@ -480,7 +179,7 @@ Replace the default background tracks with your own audio files.
 4. Enable/Disable - Toggle background music
 5. Preview current - Sample your music
 
-Configure via: `npx agentvibes` → Music tab
+Configure now: `npx agentvibes config music`
 
 **Security Certified:** See full audit report at `docs/security/SECURITY-AUDIT.md`
 
@@ -488,24 +187,14 @@ Configure via: `npx agentvibes` → Music tab
 
 ### 🎯 Key Features
 
-**🌟 v4.2 — BMAD Party Mode & SSH Receiver:**
-- 🎭 **BMAD Party Mode Voices** — Each agent speaks with their unique voice, music, reverb, personality
-- 🖥️ **SSH Receiver Tab** — Stream TTS audio from headless servers to your local machine over TCP
-- 🎛️ **BMad Tab (TUI)** — Visual agent configurator with auto-assign and bulk edit
-- ⚡ **TTS Latency -1s** — Batched Node.js calls, inotifywait queue, background cleanup
-- 🎨 **ANSI Banner Colors Restored** — Gold/cyan/traffic-light colors in TTS info banner
-- 🔕 **Banner Toggle** — Hide TTS banner without muting (`~/.agentvibes/banner-disabled`)
-- 🔇 **No Party Mode Overlap** — Agents wait for full audio before next speaks
-- 🧹 **Markdown-Clean Speech** — Asterisks/formatting stripped automatically from party mode
-
-**🌟 NEW IN v3.6.0 — Voice Explorer Release:**
-- 🏷️ **Friendly Voice Names** - "Ryan" instead of "en_US-libritts_r-medium-speaker-123"
-- 💬 **Intro Text (Pretext)** - Custom prefix for all TTS ("FireBot: Starting...")
-- 🎵 **Custom Background Music** - Upload your own audio files with battle-tested security
-- 🎨 **Interactive Installer** - Preview voices and music during installation
-- 🛡️ **Security Hardening** - 180+ attack variations tested, 100% blocked, OWASP compliant
-
-**🪟 NEW IN v3.5.5 — Native Windows Support:**
+**🎛️ NEW IN v5.4.0 — TUI Installer & Fixes:**
+- 🖥️ **TUI Installer** - Interactive terminal UI: browse voices, configure providers, enable BMAD party mode
+- 🔧 **Spinner Fix** - Resolved `spinner.info is not a function` crash on WSL/Linux
+- 🐛 **Circular Dependency Fix** - Removed self-referential `agentvibes@^3.5.9` dep that silently broke installs
+- 🎵 **Background Music Volume Fix** - Restored `bg_volume="0.20"` fallback in `audio-processor.sh`
+- 📂 **PROJECT_ROOT Fix** - `play-tts.sh` now correctly resolves project root for per-project config
+
+**🪟 v3.5.5 — Native Windows Support:**
 - 🖥️ **Windows Native TTS** - Soprano, Piper, and Windows SAPI providers. No WSL required!
 - 🎵 **Background Music** - 16 genre tracks mixed under voice
 - 🎛️ **Reverb & Audio Effects** - 5 reverb levels via ffmpeg
@@ -522,7 +211,7 @@ Configure via: `npx agentvibes` → Music tab
 - 🎭 **Multi-Provider Support** - Soprano (neural), Piper TTS (50+ free voices), macOS Say (100+ built-in), or Windows SAPI
 - 🎙️ **27+ Professional AI Voices** - Character voices, accents, and unique personalities
 - 🎙️ **Verbosity Control** - Choose how much Claude speaks (LOW, MEDIUM, HIGH)
-- 🎙️ **AgentVibes MCP** - Natural language control ("Switch to Aria voice") for Claude Code & Desktop
+- 🎙️ **AgentVibes MCP** - Natural language control ("Switch to Aria voice") for Claude Code, Desktop & Warp
 - 🔊 **SSH Audio Optimization** - Auto-detects remote sessions and eliminates static (VS Code Remote SSH, cloud dev)
 
 **🎭 Personalization:**
@@ -563,11 +252,10 @@ All 50+ Piper voices AgentVibes provides are sourced from Hugging Face's open-so
 - [📋 Prerequisites](#-prerequisites) - What you actually need (Node.js + optional tools)
 - [✨ What is AgentVibes?](#-what-is-agentvibes) - Overview & key features
 - [🌟 NEW FEATURE HIGHLIGHTS](#-new-feature-highlights) - **START HERE!**
-  - [🎭 BMAD Party Mode](#-bmad-party-mode--multi-agent-voice-conversations) - Per-agent voices, music, reverb
-  - [🖥️ SSH Receiver](#️-agentvibes-receiver--remote-audio-streaming) - Stream audio from headless servers
+  - [🎤 Voice Browser v1.0](#-agent-vibes-v10-voice-browser) - Browse & sample 914 voices
   - [💬 Intro Text](#-intro-text-pretext---your-personal-ai-branding) - Custom TTS prefixes
   - [🎵 Custom Background Music](#-custom-background-music---complete-audio-control) - Upload your own tracks
-- [📰 Latest Release](#-latest-release) - v4.6.7 — Party mode TTS fixes
+- [📰 Latest Release](#-latest-release) - v3.6.0 "Voice Explorer" with Voice Browser, Friendly Names, Custom Music
 - [🪟 Windows Setup Guide for Claude Desktop](mcp-server/WINDOWS_SETUP.md) - Complete Windows installation with WSL & Python
 
 ### AgentVibes MCP (Natural Language Control)
@@ -577,6 +265,7 @@ All 50+ Piper voices AgentVibes provides are sourced from Hugging Face's open-so
   - [For Claude Code](docs/mcp-setup.md#for-claude-code) - Project-specific setup
 
 ### Core Features
+- [🎤 AgentVibes Voice Browser](#-agentvibes-voice-browser) - **Browse and sample 914 voices interactively**
 - [🎤 Commands Reference](#-commands-reference) - All available commands
 - [🎙️ Verbosity Control](#%EF%B8%8F-verbosity-control) - Control how much Claude speaks (low/medium/high)
 - [🎭 Personalities vs Sentiments](#-personalities-vs-sentiments) - Two systems explained
@@ -585,7 +274,6 @@ All 50+ Piper voices AgentVibes provides are sourced from Hugging Face's open-so
 - [🎙️ AgentVibes Receiver - NEW!](#%EF%B8%8F-agentvibes-receiver-remote-audio-streaming-from-voiceless-servers) - Remote audio streaming from voiceless servers
 
 ### Integrations & Platforms
-- [🤝 GitHub Copilot Integration](#-github-copilot-integration) - Use AgentVibes TTS with GitHub Copilot CLI
 - [🤖 OpenClaw Integration](#-openclaw-integration) - Use AgentVibes with OpenClaw messaging platform
   - [🎙️ AgentVibes Skill for OpenClaw](#-agentvibes-skill-for-openclaw---what-you-get) - 50+ voices, effects, personalities for OpenClaw
   - [📱 AgentVibes Receiver](#-agentvibes-receiver-local-phone-) - Remote audio on phones/local machines
@@ -595,7 +283,6 @@ All 50+ Piper voices AgentVibes provides are sourced from Hugging Face's open-so
 - [💡 Common Workflows](#-common-workflows) - Quick examples
 - [🔧 Advanced Features](#-advanced-features) - Custom voices & personalities
 - [🔊 Remote Audio Setup](#-remote-audio-setup) - Play TTS from remote servers
-- [🛠️ Technical Documentation](#️-technical-documentation) - Audio architecture, cross-platform support, voice resolution
 - [🚨 Security Hardening Guide](docs/security-hardening-guide.md) - **REQUIRED if running OpenClaw on remote server**: SSH hardening, Fail2Ban, Tailscale, UFW, AIDE
 - [🔬 Technical Deep Dive](docs/technical-deep-dive.md) - How AgentVibes works under the hood
 - [❓ Troubleshooting](#-troubleshooting) - Common issues & fixes
@@ -614,87 +301,97 @@ All 50+ Piper voices AgentVibes provides are sourced from Hugging Face's open-so
 
 ## 📰 Latest Release
 
-**[v4.6.7 - Party Mode TTS Fixes](https://github.com/paulpreibisch/AgentVibes/releases/tag/v4.6.7)**
-
-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.
-
-### 🐛 Recent Fixes (v4.6.3 / v4.6.4)
-
-- **Party mode correct voices** — agents now speak with their individually configured voices. `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.
-- **macOS CI green** — `mktemp` with extension suffix (e.g. `tts-XXXXXX.wav`) silently fails on BSD mktemp. Fixed all 12 occurrences across the TTS pipeline scripts.
-- **macOS path symlink test fix** — `/var/folders/...` resolved to `/private/var/folders/...` in test assertions.
+**[v3.6.0 - "Voice Explorer" Release](https://github.com/paulpreibisch/AgentVibes/releases/tag/v3.6.0)** 🎉
 
-### 🎭 BMAD Party Mode — Multi-Agent Voice Conversations
+### 🎤 AgentVibes Voice Browser
 
-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:
+**Browse and sample 914 voices in real-time!**
 
 ```bash
-npx agentvibes   # Press B for BMad Tab
+npx agentvibes-voice-browser
 ```
 
-**Each agent gets:**
-- 🎙️ **Their own voice** — 914 to choose from, or auto-assign gender-aware
-- 🎵 **Their own music track** — cinematic for the Architect, lo-fi for the Dev
-- 🎚️ **Their own volume** — fine-tune per-agent, or bulk-set all at once
-- 🎛️ **Their own reverb** — studio, hall, cathedral, room, or none
-- 💬 **Their own pretext** — "Winston says:..." before every line
-- 🎭 **Their own personality** — sarcastic, dramatic, pirate, cheerful...
-- 🔇 **No overlap** — agents wait for full audio before the next one speaks
-- ✨ **Markdown stripped** — no "asterisk asterisk" in TTS output
-
-### 🎛️ BMad Tab — Full Visual Agent Configurator
-
-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 |
+Interactive console browser with:
+- 🎧 Real-time voice sampling - hear before you choose
+- ⭐ Favorite system - mark your top voices
+- 🔍 Search & filter - find voices by personality, accent, gender
+- 📦 One-click install - install directly from browser
+- 🎨 Beautiful UI - stunning console interface
 
-The table shows **Voice, Gender, Provider, Reverb, Music, Vol, Pretext** columns. Voice names are automatically beautified: `16Speakers::Rose_Ibex` → `Rose Ibex`.
+**914 Total Voices:**
+- 904 Piper speaker variations (libritts-high)
+- 10 curated personality voices
 
-### 🖥️ SSH Receiver — Hear Your Headless Server
+### 🎯 Major Features
 
-Stream TTS from a cloud box, WSL2, or any voiceless server directly to your local machine over TCP:
+**🏷️ Friendly Voice Names**
+- No more cryptic IDs! Switch voices with names like "Ryan", "Joe", "Sarah"
+- All 904+ voices have memorable, personality-matched names
+- Voice metadata includes personalities, accents, and recommendations
 
 ```bash
-# Local: open TUI → Receiver tab → Start
-npx agentvibes
-
-# Remote: AgentVibes auto-detects the receiver and streams audio to you
+# Before: /agent-vibes:switch en_US-libritts_r-medium-speaker-123
+# After:
+/agent-vibes:switch Ryan
 ```
 
-### ⚡ ~1 Second Faster TTS
+**💬 Intro Text (Pretext) Feature**
+- Custom prefix for all TTS announcements
+- Set during installation or anytime after
+- Perfect for personal branding: "FireBot: Starting analysis..."
+- Up to 50 characters, UTF-8 and emoji support
 
-- 6 Node.js profile reads collapsed into 1 (~900ms saved per speech)
-- `inotifywait` queue worker — no polling delay
-- Cache cleanup runs off the critical path
+```bash
+npx agentvibes config intro-text
+```
 
-### 🎨 ANSI Colors Restored + Banner Toggle
+**🎵 Custom Background Music**
+- Upload your own audio files (.mp3, .wav, .ogg, .m4a)
+- **Battle-tested security:** 180+ attack variations blocked
+- Magic number validation ensures real audio files
+- File ownership verification (UID checks)
+- Audio duration validation (30-90s recommended, 300s max)
+- Secure storage with 600 permissions
+- Perfect for team audio branding
 
-Full color in the TTS banner. Silence it without muting audio:
 ```bash
-touch ~/.agentvibes/banner-disabled   # or: "turn off the TTS banner" via MCP
+npx agentvibes config music
 ```
 
+**🎨 Interactive Installer**
+- Preview voices during installation
+- Sample all 16 background music tracks
+- Audio environment auto-detection
+- Cross-platform preview support
+
+**🛡️ Security Hardening**
+- **180+ attack variations tested** - Path traversal, symlinks, Unicode, null bytes
+- **100% attack rejection rate** - All malicious attempts blocked
+- **OWASP compliant** - CWE-22 path traversal prevention verified
+- **Production certified** - Comprehensive security audit completed
+- **Defense-in-depth** - 7 validation layers protect your system
+- File ownership verification and secure storage (600 permissions)
+- Security audit report: `docs/security/SECURITY-AUDIT.md`
+
 ### Quick Install
 
 ```bash
+# Install AgentVibes
 npx agentvibes install
+
+# Launch Voice Browser
+npx agentvibes-voice-browser
 ```
 
-💡 **Tip:** If `npx agentvibes` shows an older version: `npm cache clean --force && npx agentvibes@latest`
+**🐞 Bug Fixes in v3.6.0:**
+- Fixed `get_verbosity` MCP tool returning wrong level after fresh install (now reads from correct project directory, defaults to `high`)
+- Fixed Voice Browser Soprano TTS detection, Custom Music race conditions, installer emoji rendering
+
+💡 **Tip:** If `npx agentvibes` shows an older version, clear cache: `npm cache clean --force && npx agentvibes@latest --help`
 
-🐛 **Found a bug?** [GitHub Issues](https://github.com/paulpreibisch/AgentVibes/issues)
+🐛 **Found a bug?** Report at [GitHub Issues](https://github.com/paulpreibisch/AgentVibes/issues)
 
-[→ View Complete Release Notes](RELEASE_NOTES.md) | [→ View Previous Release (v4.0.1)](https://github.com/paulpreibisch/AgentVibes/releases/tag/v4.0.1) | [→ View All Releases](https://github.com/paulpreibisch/AgentVibes/releases)
+[→ View Complete Release Notes](RELEASE_NOTES_v3.6.0.md) | [→ View All Releases](https://github.com/paulpreibisch/AgentVibes/releases)
 
 [↑ Back to top](#-table-of-contents)
 
@@ -746,20 +443,6 @@ Just code normally - AgentVibes automatically speaks task acknowledgments and co
 
 ---
 
-### TUI Console Commands
-
-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):**
 ```bash
 brew install bash  # Required for bash 5.x features
@@ -772,6 +455,64 @@ macOS ships with bash 3.2 (from 2007). After this, everything works perfectly!
 
 [↑ Back to top](#-table-of-contents)
 
+---
+
+## 🎤 AgentVibes Voice Browser
+
+**The easiest way to find your perfect voice!**
+
+### Launch the Browser
+
+```bash
+npx agentvibes-voice-browser
+```
+
+### Features
+
+- **914 Voices** - Browse 904 Piper speakers + 10 curated voices
+- **Real-Time Sampling** - Press ENTER to hear any voice instantly
+- **Favorite System** - Mark favorites for quick access
+- **Smart Search** - Filter by name, personality, accent, or gender
+- **One-Click Install** - Press 'I' to install and switch to a voice
+- **Beautiful UI** - Stunning console interface with blessed.js
+
+### Keyboard Shortcuts
+
+| Key | Action |
+|-----|--------|
+| **ENTER** | Play voice sample |
+| **I** | Install/Select voice for AgentVibes |
+| **F** | Toggle favorite |
+| **/** | Search voices |
+| **ESC** | Clear search / Back |
+| **↑/↓** | Navigate list |
+| **G** | Jump to top |
+| **Shift+G** | Jump to bottom |
+| **H** | Show help |
+| **Q** | Quit |
+
+### Voice Categories
+
+**Curated Voices** (10 hand-picked personalities):
+- Professional, Friendly, Authoritative, Warm, Energetic
+- Technical, Calm, Narrator, Conversational, Enthusiastic
+
+**Speaker Variations** (904 from libritts-high):
+- Male and female speakers
+- Various accents and tones
+- High-quality neural voices
+- Unique characteristics
+
+### Finding Your Perfect Voice
+
+1. **Launch browser:** `npx agentvibes-voice-browser`
+2. **Search by trait:** Press `/` and type "friendly" or "professional"
+3. **Sample voices:** Navigate with arrows, press ENTER to hear
+4. **Mark favorites:** Press 'F' on voices you like
+5. **Install:** Press 'I' to set as your AgentVibes voice
+
+**Pro Tip:** Use the search to find voices matching your project's mood!
+
 [↑ Back to top](#-table-of-contents)
 
 ---
@@ -1119,11 +860,24 @@ AgentVibes provides **50+ slash commands** and **natural language MCP equivalent
 
 **[→ View Complete Command Reference](docs/commands.md)** - All voice, system, personality, sentiment, language, and BMAD commands with MCP equivalents
 
+### Voice Browser Commands
+
+```bash
+# Launch voice browser
+npx agentvibes-voice-browser
+
+# Or use global command (if installed globally)
+agentvibes-voice-browser
+```
+
+**MCP Equivalent:** Currently CLI-only (no MCP command)
+
 ### Intro Text Commands
 
 ```bash
-# Configure intro text — open Settings tab
-npx agentvibes
+# Configure intro text
+/agent-vibes:config intro-text
+npx agentvibes config intro-text
 
 # View current intro text
 cat ~/.claude/config/intro-text.txt
@@ -1139,8 +893,16 @@ cat ~/.claude/config/intro-text.txt
 ### Custom Music Commands
 
 ```bash
-# Configure background music — open Music tab
-npx agentvibes
+# Configure background music
+/agent-vibes:config music
+npx agentvibes config music
+
+# Menu options:
+# 1. Change music - Upload new audio file
+# 2. Remove music - Clear custom music
+# 3. Reset to default - Restore built-in tracks
+# 4. Enable/Disable - Toggle background music
+# 5. Preview current - Sample current music
 ```
 
 **MCP Equivalent:**
@@ -1248,7 +1010,7 @@ Every task acknowledgment plays **twice** - first in English, then in your targe
 
 ## 🗣️ Voice Library
 
-Use the **AgentVibes TUI installer** (`/audio-browser`) to browse, sample, and install from 914 voices interactively.
+**NEW in v3.6.0:** Use the **[AgentVibes Voice Browser](#-agentvibes-voice-browser)** to browse, sample, and install from 914 voices! Launch with `npx agentvibes-voice-browser`.
 
 ### Friendly Voice Names
 
@@ -1341,85 +1103,6 @@ This design means **any TTS provider** can integrate with BMAD by replacing thes
 
 ---
 
-## 🤝 GitHub Copilot Integration
-
-**Use AgentVibes with GitHub Copilot in VS Code — same voices, same personalities, same MCP tools!**
-
-Copilot discovers AgentVibes through two mechanisms:
-
-1. **`.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)
-2. **`.vscode/mcp.json`** — registers the AgentVibes MCP server so Copilot can call `text_to_speech`, `set_voice`, and other tools
-
-### Setup
-
-**Step 1: Install AgentVibes** (if you haven't already)
-
-```bash
-npx agentvibes install
-```
-
-**Step 2: Configure VS Code MCP**
-
-Open the AgentVibes console and go to the **LLM** tab (press `L`):
-
-```bash
-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:
-
-```json
-{
-  "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.
-
-### What Copilot Can Do
-
-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 |
-
-### BMAD Party Mode
-
-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.
-
-### Differences from 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 |
-
-[↑ Back to top](#-table-of-contents)
-
----
-
 ## 🤖 OpenClaw Integration
 
 **Use AgentVibes TTS with OpenClaw - the revolutionary AI assistant you can access via any instant messenger!**
@@ -2199,19 +1882,19 @@ Both do the exact same thing - MCP is more convenient, slash commands are more t
 - **Optional**: sox (audio effects), ffmpeg (background music, padding)
 - All TTS generation works without optional dependencies - they just enhance the experience
 
-### Voice Features
+### Voice Browser & New Features
 
-**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: How do I use the Voice Browser?**
+**A:** Simply run `npx agentvibes-voice-browser` and you'll see an interactive console with 914 voices. Use arrow keys to navigate, ENTER to sample voices, 'I' to install, 'F' to favorite, and '/' to search.
 
 **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.
+**A:** During installation, you'll be prompted for intro text. You can also configure it anytime with `npx agentvibes config intro-text`. 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.
+**A:** Yes! Run `npx agentvibes config music` and select "Change music". 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.
@@ -2219,11 +1902,14 @@ Both do the exact same thing - MCP is more convenient, slash commands are more t
 **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: Can I favorite voices without installing them?**
+**A:** Yes! In the Voice Browser, press 'F' to mark any voice as a favorite. Favorites are saved and you can filter to show only favorites later.
+
 **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.
+**A:** Yes! When configuring custom music with `npx agentvibes config music`, you can 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: