@kajidog/mcp-tts-voicevox 0.4.0 → 0.6.0

package/README.md

@@ -9,15 +9,35 @@ A text-to-speech MCP server using VOICEVOX
 ## What You Can Do
 
 - **Make your AI assistant speak** — Text-to-speech from MCP clients like Claude Desktop
+- **UI Audio Player (MCP Apps)** — Play audio directly in the chat with an interactive player
 - **Multi-character conversations** — Switch speakers per segment in a single call
 - **Smooth playback** — Queue management, immediate playback, prefetching, streaming
 - **Cross-platform** — Works on Windows, macOS, Linux (including WSL)
 
+## UI Audio Player (MCP Apps)
+
+![Single track player](docs/images/single-player.png)
+
+The `speak_player` tool uses [MCP Apps](https://github.com/modelcontextprotocol/ext-apps) to render an interactive audio player directly inside the chat. Unlike the standard `speak` tool which plays audio on the server, **audio is played on the client side (in the browser/app)** — no audio device needed on the server.
+
+### Features
+
+- **Client-side playback** — Audio plays in Claude Desktop's chat, not on the server. Works even over remote connections.
+- **Play/Pause controls** — Full playback controls embedded in the conversation
+- **Multi-speaker dialogue** — Sequential playback of multiple speakers in one player with track navigation
+- **Speaker switching** — Change the voice of any segment directly from the player UI
+
+| Multi-speaker playback | Track list | Speaker selection |
+|:---:|:---:|:---:|
+| ![Multi-speaker player](docs/images/multi-player.png) | ![Track list](docs/images/list-player.png) | ![Speaker selection](docs/images/select-player.png) |
+
+> **Note:** `speak_player` requires a host that supports MCP Apps (e.g., Claude Desktop). In hosts without MCP Apps support, the tool is not available and `speak` (server-side playback) can be used instead.
+
 ## Quick Start
 
 ### Requirements
 
-- Node.js 18.0.0 or higher
+- Node.js 18.0.0 or higher (or [Bun](https://bun.sh/))
 - [VOICEVOX Engine](https://voicevox.hiroshiba.jp/) (must be running)
 - ffplay (optional, recommended)
 
@@ -88,6 +108,11 @@ Config file location:
 }
 ```
 
+> 💡 Bun を使う場合は `npx` を `bunx` に置き換えるだけでOK:
+> ```json
+> "command": "bunx", "args": ["@kajidog/mcp-tts-voicevox"]
+> ```
+
 **3. Restart Claude Desktop**
 
 That's it! Ask Claude to "say hello" and it will speak!
@@ -129,11 +154,11 @@ The main feature callable from Claude.
 
 | Tool | Description |
 |------|-------------|
+| `speak_player` | Speak with UI audio player (disable with `--disable-tools`) |
 | `ping_voicevox` | Check VOICEVOX Engine connection |
 | `get_speakers` | Get list of available speakers |
 | `get_speaker_detail` | Get speaker details |
 | `stop_speaker` | Stop playback and clear queue |
-| `generate_query` | Generate speech synthesis query |
 | `synthesize_file` | Generate audio file |
 
 </details>
@@ -176,9 +201,15 @@ Restrict AI from specifying certain options.
 
 ```bash
 # Disable unnecessary tools
-export VOICEVOX_DISABLED_TOOLS=generate_query,synthesize_file
+export VOICEVOX_DISABLED_TOOLS=get_speaker_detail,synthesize_file
 ```
 
+### UI Player Settings
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `VOICEVOX_AUTO_PLAY` | Auto-play audio in UI player | `true` |
+
 ### Server Settings
 
 | Variable | Description | Default |
@@ -207,7 +238,7 @@ npx @kajidog/mcp-tts-voicevox --http --port 8080
 npx @kajidog/mcp-tts-voicevox --restrict-immediate --restrict-wait-for-end
 
 # Disable tools
-npx @kajidog/mcp-tts-voicevox --disable-tools generate_query,synthesize_file
+npx @kajidog/mcp-tts-voicevox --disable-tools get_speaker_detail,synthesize_file
 ```
 
 | Argument | Description |
@@ -225,6 +256,7 @@ npx @kajidog/mcp-tts-voicevox --disable-tools generate_query,synthesize_file
 | `--restrict-wait-for-start` | Restrict waitForStart |
 | `--restrict-wait-for-end` | Restrict waitForEnd |
 | `--disable-tools <tools>` | Disable tools |
+| `--auto-play` / `--no-auto-play` | Auto-play in UI player |
 | `--http` | HTTP mode |
 | `--port <value>` | HTTP port |
 | `--host <value>` | HTTP host |
@@ -383,6 +415,7 @@ curl http://localhost:50021/speakers
 |---------|-------------|
 | `@kajidog/mcp-tts-voicevox` | MCP server |
 | [`@kajidog/voicevox-client`](https://www.npmjs.com/package/@kajidog/voicevox-client) | General-purpose VOICEVOX client library (can be used independently) |
+| `@kajidog/player-ui` | React-based audio player UI for browser playback |
 
 ---
 
@@ -406,6 +439,8 @@ pnpm install
 | `pnpm lint` | Run lint |
 | `pnpm dev` | Start dev server |
 | `pnpm dev:stdio` | Dev with stdio mode |
+| `pnpm dev:bun` | Start dev server with Bun |
+| `pnpm dev:bun:http` | Start HTTP dev server with Bun |
 
 </details>
 

package/dist/index.d.ts

@@ -1,3 +1 @@
 #!/usr/bin/env node
-export {};
-//# sourceMappingURL=index.d.ts.map