dsh-audiogen 0.4.14 → 0.4.15

package/README.md

@@ -20,7 +20,7 @@
 - **Prompt enhancement**: rewrite a rough idea into a ready-to-generate description with an LLM (pick any model from *Settings → Models*; falls back to the agent default model)
 - **History with one-click restore**: prompt, config, model set *and the original audio* come back into the panel — no regeneration, no extra cost
 - **Resource library**: auto-save generated audio (or opt in per run), organized by type — voices / music / SFX / TTS — with search, tags, rename, category moves, and full provenance (channel, model, voice id, prompt, params snapshot). Reuse a voice or music bed instead of regenerating
-- **Agent tools**: `generate_audio` and `search_audio_library`, plus bundled session skills — the Agent can generate and find audio on demand
+- **Agent tools**: `generate_audio` and `search_audio_library`, `manage_audio_voices` (vendor voice browsing/deletion), plus bundled session skills — the Agent can generate and find audio on demand
 - **Keys stay local**: API keys live in the local DSH settings document and generation is proxied by the local host; the browser and the Agent never touch plaintext credentials
 
 ## 📸 Screenshots
@@ -78,6 +78,7 @@ Restart `dsh web` after install — the sidebar will show the **AI Audio** entry
 | Tool | Purpose |
 | --- | --- |
 | `generate_audio` | Submit a TTS / music / SFX / voice-design task; waits for completion and returns same-origin audio URLs. Optional `enhance_prompt`, `save_to_library`, per-vendor params. |
+| `manage_audio_voices` | Browse/filter the vendor voice libraries (MiniMax, ElevenLabs) with language/keyword/source filters, and delete account-owned voices (official/shared/system voices are read-only and refused). Then use the returned `voice_id` with `generate_audio` (mode=tts). |
 | `search_audio_library` | Search the local resource library (type / category / keyword) and reuse an existing voice, music bed or effect. |
 
 Typical session commands (skills bundled with the plugin):

package/README.zh-CN.md

@@ -20,7 +20,7 @@
 - **✨ 提示词增强**：把一句粗略想法扩写成适合生成模型的完整描述，LLM 模型可在「设置 → 模型」中任选（缺省跟随 Agent 默认模型，无需额外 API Key）
 - **历史记录一键恢复**：prompt、配置、模型组合**以及当时的音频**全部回到面板——可直接试听/下载，无需重新生成、不额外消耗
 - **资源库**：生成后可一键入库（或设置自动保存），按类型分目录——音色 voice / 音乐 music / 音效 sfx / TTS——支持搜索、标签、重命名、移动分类，并保留完整溯源（渠道、模型、voiceId、提示词、参数快照）。同款音色/配乐/音效直接复用，不必重复生成
-- **Agent 工具**：`generate_audio` 与 `search_audio_library`，并随包分发 TTS/音乐/音效/音色设计会话技能
+- **Agent 工具**：`generate_audio`、`search_audio_library` 与 `manage_audio_voices`（厂商音色浏览/删除），并随包分发 TTS/音乐/音效/音色设计会话技能
 - **密钥留在本机**：API 密钥存于本地 DSH 设置文档，生成请求由本地宿主代理转发，浏览器与 Agent 全程不接触明文密钥
 
 ## 📸 截图
@@ -78,6 +78,7 @@ dsh plugin --profile web add /path/to/dsh-audiogen
 | 工具 | 用途 |
 | --- | --- |
 | `generate_audio` | 提交 TTS / 音乐 / 音效 / 音色设计任务，等待完成后返回同源音频 URL；支持 `enhance_prompt`、`save_to_library` 与各厂商参数。 |
+| `manage_audio_voices` | 浏览/筛选厂商音色库（MiniMax、ElevenLabs，支持语言/关键词/来源筛选），删除账户自有音色（官方/共享/系统音色只读并拒绝）；随后把返回的 `voice_id` 交给 `generate_audio`（mode=tts）即可生成。 |
 | `search_audio_library` | 检索本地资源库（类型/分类/关键词），复用已有音色、配乐或音效。 |
 
 会话内常用指令（插件自带技能）：