Convert text to speech using Microsoft Edge neural voices and generate MP3 audio.
npx skills add https://github.com/haomingz/kimi-skills --skill speech-synthesis
Please help me install this Agent Skill. Skill: speech-synthesis Source: https://github.com/haomingz/kimi-skills/tree/main/skills/speech-synthesis Command: npx skills add https://github.com/haomingz/kimi-skills --skill speech-synthesis
将文本转换为高质量语音，支持多语言、多种音色，可调节语速、音调和音量，并生成字幕，输出MP3音频文件。当你需要朗读文本（比如文章、消息）、为视频或演示文稿生成配音，或直接提到“TTS”、“文字转语音”、“配音”、“朗读”时，就会使用这个技能。
输入要转换为语音的文本，并可选择音色、语言和输出格式，即可生成音频文件。
High-intent search queries and answers about installing and using this skill.
This text-to-speech tool converts text to natural speech by using Microsoft Edge neural voices to generate MP3 audio, supporting multiple languages with adjustable rate, pitch, and volume.
Yes, this text-to-speech process supports subtitle generation alongside MP3 audio output, facilitating accessible video and content presentation.
Yes, the voice synthesis process allows you to adjust rate, pitch, and volume for Microsoft Edge neural voices before outputting the final MP3 audio file.
Yes, you need the node-edge-tts dependency installed to execute this text-to-speech functionality, as it provides the Microsoft Edge neural voices required to synthesize MP3 audio.
The best way to generate voiceovers for presentations is to use this text-to-speech capability, leveraging Microsoft Edge neural voices to customize voice, rate, pitch, and output MP3 files with subtitles.
Aliisa-ytManage TTS synthesis, playback, and temporary file cleanup queues.
jkitchinAssemble six-scene MP4 videos from images and narrated audio using ffmpeg.
ragnarokhaaTranscribe spoken audio into text using OpenAI's Whisper model.
winsorllcConvert text into audible speech via system TTS or Web Speech API.
