@kajidog/mcp-tts-voicevox 0.5.0 → 0.6.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -9,10 +9,30 @@ A text-to-speech MCP server using VOICEVOX
9
9
  ## What You Can Do
10
10
 
11
11
  - **Make your AI assistant speak** — Text-to-speech from MCP clients like Claude Desktop
12
+ - **UI Audio Player (MCP Apps)** — Play audio directly in the chat with an interactive player
12
13
  - **Multi-character conversations** — Switch speakers per segment in a single call
13
14
  - **Smooth playback** — Queue management, immediate playback, prefetching, streaming
14
15
  - **Cross-platform** — Works on Windows, macOS, Linux (including WSL)
15
16
 
17
+ ## UI Audio Player (MCP Apps)
18
+
19
+ ![Single track player](docs/images/single-player.png)
20
+
21
+ 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.
22
+
23
+ ### Features
24
+
25
+ - **Client-side playback** — Audio plays in Claude Desktop's chat, not on the server. Works even over remote connections.
26
+ - **Play/Pause controls** — Full playback controls embedded in the conversation
27
+ - **Multi-speaker dialogue** — Sequential playback of multiple speakers in one player with track navigation
28
+ - **Speaker switching** — Change the voice of any segment directly from the player UI
29
+
30
+ | Multi-speaker playback | Track list | Speaker selection |
31
+ |:---:|:---:|:---:|
32
+ | ![Multi-speaker player](docs/images/multi-player.png) | ![Track list](docs/images/list-player.png) | ![Speaker selection](docs/images/select-player.png) |
33
+
34
+ > **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.
35
+
16
36
  ## Quick Start
17
37
 
18
38
  ### Requirements
@@ -134,11 +154,11 @@ The main feature callable from Claude.
134
154
 
135
155
  | Tool | Description |
136
156
  |------|-------------|
157
+ | `speak_player` | Speak with UI audio player (disable with `--disable-tools`) |
137
158
  | `ping_voicevox` | Check VOICEVOX Engine connection |
138
159
  | `get_speakers` | Get list of available speakers |
139
160
  | `get_speaker_detail` | Get speaker details |
140
161
  | `stop_speaker` | Stop playback and clear queue |
141
- | `generate_query` | Generate speech synthesis query |
142
162
  | `synthesize_file` | Generate audio file |
143
163
 
144
164
  </details>
@@ -181,9 +201,15 @@ Restrict AI from specifying certain options.
181
201
 
182
202
  ```bash
183
203
  # Disable unnecessary tools
184
- export VOICEVOX_DISABLED_TOOLS=generate_query,synthesize_file
204
+ export VOICEVOX_DISABLED_TOOLS=get_speaker_detail,synthesize_file
185
205
  ```
186
206
 
207
+ ### UI Player Settings
208
+
209
+ | Variable | Description | Default |
210
+ |----------|-------------|---------|
211
+ | `VOICEVOX_AUTO_PLAY` | Auto-play audio in UI player | `true` |
212
+
187
213
  ### Server Settings
188
214
 
189
215
  | Variable | Description | Default |
@@ -212,7 +238,7 @@ npx @kajidog/mcp-tts-voicevox --http --port 8080
212
238
  npx @kajidog/mcp-tts-voicevox --restrict-immediate --restrict-wait-for-end
213
239
 
214
240
  # Disable tools
215
- npx @kajidog/mcp-tts-voicevox --disable-tools generate_query,synthesize_file
241
+ npx @kajidog/mcp-tts-voicevox --disable-tools get_speaker_detail,synthesize_file
216
242
  ```
217
243
 
218
244
  | Argument | Description |
@@ -230,6 +256,7 @@ npx @kajidog/mcp-tts-voicevox --disable-tools generate_query,synthesize_file
230
256
  | `--restrict-wait-for-start` | Restrict waitForStart |
231
257
  | `--restrict-wait-for-end` | Restrict waitForEnd |
232
258
  | `--disable-tools <tools>` | Disable tools |
259
+ | `--auto-play` / `--no-auto-play` | Auto-play in UI player |
233
260
  | `--http` | HTTP mode |
234
261
  | `--port <value>` | HTTP port |
235
262
  | `--host <value>` | HTTP host |
@@ -388,6 +415,7 @@ curl http://localhost:50021/speakers
388
415
  |---------|-------------|
389
416
  | `@kajidog/mcp-tts-voicevox` | MCP server |
390
417
  | [`@kajidog/voicevox-client`](https://www.npmjs.com/package/@kajidog/voicevox-client) | General-purpose VOICEVOX client library (can be used independently) |
418
+ | `@kajidog/player-ui` | React-based audio player UI for browser playback |
391
419
 
392
420
  ---
393
421
 
package/dist/index.d.ts CHANGED
@@ -1,3 +1 @@
1
1
  #!/usr/bin/env node
2
- export {};
3
- //# sourceMappingURL=index.d.ts.map