Convert AI-generated text to speech via CLI and REST API endpoints.
npx skills add https://github.com/CyangZhou/-2--Project-Yunshu- --skill -cyangzhou
Please help me install this Agent Skill. Skill: 语音播报 Source: https://github.com/CyangZhou/-2--Project-Yunshu-/tree/main/skills/%E8%AF%AD%E9%9F%B3%E6%92%AD%E6%8A%A5 Command: npx skills add https://github.com/CyangZhou/-2--Project-Yunshu- --skill -cyangzhou
当您在编写代码或调试时需要快速获取 AI 回复的内容但无法持续查看屏幕时，语音播报技能将文本转换为语音输出，解放双眼并提升工作效率。
在命令行中传入要播报的文本即可触发语音播报。
High-intent search queries and answers about installing and using this skill.
To convert AI text replies to speech while coding, this Skill uses pyttsx3 to synthesize audio locally, freeing your eyes from the screen during development and debugging sessions.
Yes, you can trigger text to speech synthesis through a lightweight Flask server exposing a REST API endpoint at /speak, alongside a /status endpoint to check operation state.
You can use pyttsx3 for local speech synthesis by passing the desired text string directly as a command line argument, which immediately triggers the audio playback workflow.
Python TTS speech synthesis supports controllable playback modes, allowing you to switch between character-by-character and full-paragraph speech for long text or code segments.
No internet access is needed because pyttsx3 performs speech synthesis locally, ensuring audio generation for coding workflows runs entirely offline without external API dependencies.
A limitation of using pyttsx3 for converting text to speech is that it relies on your operating system's built-in local voices, meaning audio quality and naturalness vary by platform.
mangiapanejohn-devGenerate local offline speech audio from text using sherpa-onnx.
aviz85Stream microphone audio to ElevenLabs Scribe v2 Realtime and write transcribed text to a temporary file.
ovachieverIntegrate Cloudflare Turnstile bot protection with server-side siteverify validation.
modu-aiGenerate multilingual speech, voice clones, and sound effects via ElevenLabs TTS.
