with one click
text-to-speech
文本转语音工具 - 支持 Edge TTS 和 Kokoro TTS (v1.1-zh) 双引擎,102 个中文音色
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
文本转语音工具 - 支持 Edge TTS 和 Kokoro TTS (v1.1-zh) 双引擎,102 个中文音色
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Automate the full QuarkPanTool → mswnlz GitHub content publishing pipeline. Use when the user provides Quark share URLs and wants: (1) create a batch folder in Quark Drive, (2) save/copy resources into that folder, (3) copy promotional files INTO each shared resource folder, (4) generate permanent encrypted share links with random passcodes, (5) auto-classify items into mswnlz repos (book/movies/etc.) by repo descriptions, (6) append/update the target repo's YYYYMM.md and README month index, (7) git commit+push, (8) send unified Telegram notifications, and (9) force-trigger mswnlz.github.io site rebuild and return the final site URLs.
Track YouTube channels for new uploads. Supports both RSS mode (no API key needed, unlimited quota) and API mode. Use when: add/remove/list tracked YouTube channels, check for new videos, or run scheduled YouTube channel monitoring.
"Upload and publish videos to YouTube with title, description, tags, thumbnail and subtitles. Use for: youtube upload, publish video, share on youtube."
扫描目录识别所有类型发票(交通、住宿、餐饮等),提取关键信息并生成分类统计报告
音频变声处理工具 - 使用 RVC AI 模型进行真实的声音转换,支持视频直接输入
通用图片生成 Skill,支持多种 AI 模型(ModelScope、Gemini、RunningHub 等),可被其他 Skills 调用
| name | text-to-speech |
| description | 文本转语音工具 - 支持 Edge TTS 和 Kokoro TTS (v1.1-zh) 双引擎,102 个中文音色 |
| version | 3.1.0 |
| changelog | [{"Sun May 17 2026 00:00:00 GMT+0000 (Coordinated Universal Time)":"v3.1.0 强化 localhost Kokoro 代理绕过规则——curl/requests 直连本地服务默认必须 NO_PROXY,不允许先走代理失败后重试"}] |
| author | M. |
将文本转换为语音,支持 Kokoro TTS v1.1-zh(本地 Docker,102 个中文音色)和 Edge TTS(在线)。
| 特性 | Kokoro TTS v1.1-zh | Edge TTS |
|---|---|---|
| 质量 | 更自然、接近真人 | 标准 Neural 语音 |
| 网络 | 不需要(本地 Docker) | 需要网络连接 |
| 中文女声 | 55 个 | 13 个 |
| 中文男声 | 44 个 | 5 个 |
| 英文音色 | 3 个 | 0(需切换英文声音) |
| 语速调节 | speed 参数 | rate/pitch/volume |
| 前提 | Docker 容器需运行 | 无 |
| 配置值 | kokoro | edge |
# 默认使用 Kokoro TTS(当前配置)
python3 ~/.claude/skills/text-to-speech/scripts/text_to_speech.py <文本文件>
# 指定引擎
python3 ~/.claude/skills/text-to-speech/scripts/text_to_speech.py script.txt --engine kokoro
python3 ~/.claude/skills/text-to-speech/scripts/text_to_speech.py script.txt --engine edge
# 指定声音
python3 ~/.claude/skills/text-to-speech/scripts/text_to_speech.py script.txt -v zf_094
# 指定输出文件
python3 ~/.claude/skills/text-to-speech/scripts/text_to_speech.py script.txt -o output.mp3
# 调整语速(Kokoro)
python3 ~/.claude/skills/text-to-speech/scripts/text_to_speech.py script.txt --speed 1.2
# 列出所有可用声音
python3 ~/.claude/skills/text-to-speech/scripts/text_to_speech.py --list-voices
使用 --list-voices 查看完整列表(102 个)。
zm_009 - 男声(默认)zf_094 - 女声(自然温柔)zf_001 - 女声zm_050 - 男声af_maple - 女声(Maple)af_sol - 女声(Sol)bf_vale - 男声(Vale)zf_XXX - 中文女声(55 个)zm_XXX - 中文男声(44 个)af_/bf_ - 英文声音(3 个)Kokoro TTS 需要 Docker 容器运行:
# 启动
cd /Users/m/document/QNSZ/project/kokoro-tts && ./start.sh
# 停止
cd /Users/m/document/QNSZ/project/kokoro-tts && ./stop.sh
# Web UI 试听
# http://localhost:8880/web/
自动识别并移除播客脚本中的注释和标记:
(00:00)[BGM渐入:...](主播声音:...) (停顿 1秒)**文本**v1.1-zh 模型支持中英文混合文本的自然朗读。
可选集成 voice-changer skill 进行变声处理。
配置文件位于:~/.claude/skills/text-to-speech/config/tts_config.json
关键配置项:
tts_engine: "kokoro" 或 "edge"(默认引擎)kokoro_tts: Kokoro 引擎配置(API URL、默认声音、语速)edge_tts: Edge 引擎配置(声音、语速、音调、音量)available_voices: 按引擎分组的可用声音列表输入文本/文件
↓
脚本解析(移除注释和标记)
↓
Kokoro TTS / Edge TTS 语音合成
↓
后处理(voice-changer,可选)
↓
输出 MP3 文件
Kokoro TTS 运行在 localhost:8880。如果系统配置了 HTTP 代理(http_proxy/https_proxy),请求 localhost 会被代理拦截导致连接失败(curl 返回 HTTP 000)。
规则:
os.environ.setdefault("no_proxy", "localhost,127.0.0.1"),通过脚本调用无需额外处理curl 测试或调用 Kokoro API,必须加 --noproxy localhost,127.0.0.1 或设置 no_proxy=localhost,127.0.0.1requests.post("http://localhost:8880/..."),必须设置 proxies={"http": None, "https": None},或使用 requests.Session(); session.trust_env = False,并设置 NO_PROXY/no_proxy=localhost,127.0.0.1,::1# 正确:绕过代理
curl --noproxy localhost,127.0.0.1 -X POST http://localhost:8880/v1/audio/speech ...
# 错误:走了代理,返回 HTTP 000
curl -X POST http://localhost:8880/v1/audio/speech ...
pip install edge-tts