@optima-chat/comfy-cli 0.9.7 → 0.9.8

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.
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: comfy-cli
3
- description: "ComfyUI CLI tool for AI agents. ALWAYS use when user wants to: generate images (生成图片/画图/图像/生成画), edit images (编辑图片/修改图片/图生图/改图), create videos (生成视频/图生视频/制作视频), manage ComfyUI workflows (工作流/ComfyUI). Uses 'comfy image', 'comfy generate', 'comfy edit', 'comfy video' commands."
3
+ description: "ComfyUI CLI tool for AI agents. ALWAYS use when user wants to: generate images (生成图片/画图/图像/生成画), edit images (编辑图片/修改图片/图生图/改图), create videos (生成视频/图生视频/制作视频), text-to-speech (TTS/语音合成/朗读/文字转语音), speech recognition (ASR/语音识别/语音转文字/转录), manage ComfyUI workflows (工作流/ComfyUI). Uses 'comfy image', 'comfy generate', 'comfy edit', 'comfy video', 'comfy tts', 'comfy asr' commands."
4
4
  ---
5
5
 
6
6
  # ComfyUI CLI
@@ -112,6 +112,23 @@ comfy edit <图像路径> "提示词" [--no-wait] [--pretty]
112
112
  - 等同于 `comfy image "提示词" -i <图像路径>`
113
113
  - 支持风格转换、细节增强等
114
114
 
115
+ **文本转语音 (TTS):**
116
+ ```bash
117
+ comfy tts "文本内容" [-o 输出路径] [--voice Cherry] [--play] [--pretty]
118
+ ```
119
+ - 使用 DashScope qwen3-tts-flash 模型
120
+ - 支持 50+ 种声音(女声:Cherry, Serena, Chelsie 等;男声:Ethan, Aiden, Brandon 等)
121
+ - 自动检测语言(中、英、日、韩、法、德等)
122
+ - `--voices` 列出所有可用声音
123
+
124
+ **语音识别 (ASR):**
125
+ ```bash
126
+ comfy asr <音频文件> [--language zh|en|ja|ko] [--pretty]
127
+ ```
128
+ - 使用 Groq Whisper (whisper-large-v3-turbo)
129
+ - 支持 mp3, wav, m4a, ogg, webm 格式
130
+ - 文件大小限制 25MB
131
+
115
132
  **生成视频:**
116
133
  ```bash
117
134
  comfy video <图像路径> [-p "运动描述"] [-b auto|dashscope|comfyui] [-r 720P|1080P] [-d 5|10|15]
@@ -244,6 +261,27 @@ comfy workflow get abc123
244
261
  comfy download abc123
245
262
  ```
246
263
 
264
+ ### 示例 10:文本转语音
265
+ ```bash
266
+ # 中文语音合成
267
+ comfy tts "你好,欢迎使用语音合成功能" -o greeting.wav
268
+
269
+ # 使用男声
270
+ comfy tts "Hello, welcome!" --voice Ethan -o hello.wav
271
+
272
+ # 生成后自动播放
273
+ comfy tts "测试语音" --play
274
+ ```
275
+
276
+ ### 示例 11:语音识别
277
+ ```bash
278
+ # 自动检测语言
279
+ comfy asr recording.mp3
280
+
281
+ # 指定语言提示
282
+ comfy asr meeting.wav --language zh
283
+ ```
284
+
247
285
  ## 重要提示
248
286
 
249
287
  - **推荐使用 `comfy image`**:统一入口,自动选择最佳后端
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@optima-chat/comfy-cli",
3
- "version": "0.9.7",
3
+ "version": "0.9.8",
4
4
  "description": "A CLI tool for ComfyUI designed for LLM interactions",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",