chichi-speech
使用 Qwen3 和专门的语音克隆提供高质量文本转语音的 RESTful 服务。针对重复使用特定语音提示进行了优化，以避免重新计算。
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install chichi-speech或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install chichi-speech⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/chichi-speech/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: chichi-speech description: A RESTful service for high-quality text-to-speech using Qwen3 and specialized voice cloning. Optimized for reusing a specific voice prompt to avoid re-computation. ---
This skill provides a FastAPI-based REST service for Qwen3 TTS, specifically configured for reusing a high-quality reference audio prompt for efficient and consistent voice cloning. This service is packaged as an installable CLI.
Prerequisites: python >= 3.10.
pip install -e .The service runs on port 9090 by default.
# Start the server (runs in foreground, use & for background or a separate terminal)
# Optional: Uudate to your own reference audio and text for voice cloning
chichi-speech --port 9090 --host 127.0.0.1 --ref-audio "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/clone_2.wav" --ref-text "Okay. Yeah. I resent you. I love you. I respect you. But you know what? You blew it! And thanks to you."Check the health/docs:
curl http://localhost:9090/docsUse cURL:
curl -X POST "http://localhost:9090/synthesize" \
-H "Content-Type: application/json" \
-d '{
"text": "Nice to meet you",
"language": "English"
}' \
--output output/nice_to_meet.wavPOST /synthesizeqwen-tts (Qwen3 model library) - By default, it uses public sample audio from Qwen3. - CRITICAL: You can provide your own reference audio using the --ref-audio and --ref-text flags.
安装 chichi-speech（采用 Qwen3-TTS 模型的本地文本转语音服务） 后，可以对 AI 说这些话来触发它
Help me get started with chichi-speech (local text-to-speech service with Qwen3-TTS model)
Explains what chichi-speech (local text-to-speech service with Qwen3-TTS model) does, walks through the setup, and runs a quick demo based on your current project
Use chichi-speech (local text-to-speech service with Qwen3-TTS model) to a RESTful service for high-quality text-to-speech using Qwen3 and s...
Invokes chichi-speech (local text-to-speech service with Qwen3-TTS model) with the right parameters and returns the result directly in the conversation
What can I do with chichi-speech (local text-to-speech service with Qwen3-TTS model) in my design & creative workflow?
将技能文件夹放到 ~/.claude/skills/chichi-speech/ 目录（个人级，所有项目可用），或 .claude/skills/chichi-speech/（项目级）。重启 AI 客户端后，用 /chichi-speech 主动调用，或让 AI 根据上下文自动发现并使用。
chichi-speech（采用 Qwen3-TTS 模型的本地文本转语音服务） 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
chichi-speech（采用 Qwen3-TTS 模型的本地文本转语音服务） 可免费安装使用。请查阅仓库了解许可证信息。
使用 Qwen3 和专门的语音克隆提供高质量文本转语音的 RESTful 服务。针对重复使用特定语音提示进行了优化，以避免重新计算。
Lists the top use cases for chichi-speech (local text-to-speech service with Qwen3-TTS model), with example commands for each scenario
Automate my design & creative tasks using chichi-speech (local text-to-speech service with Qwen3-TTS model)
Identifies repetitive steps in your workflow and sets up chichi-speech (local text-to-speech service with Qwen3-TTS model) to handle them automatically
chichi-speech（采用 Qwen3-TTS 模型的本地文本转语音服务） 属于「Design & Creative」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。