Turn any song into an AI cover, clone voices with zero-shot cloning, and generate natural speech in 100+ languages — all running locally on your machine.将任意歌曲制作成 AI 翻唱，用零样本克隆还原人声，还能以 100+ 语言生成自然语音——全部在你的电脑本地运行。
Create realistic AI covers from any song. Powered by AICover-v0.1 and state-of-the-art vocal conversion, right on your desktop.将任意歌曲制作为逼真的 AI 翻唱。基于 AICover-v0.1 与业界领先的人声转换技术，在桌面端即可完成。
Clone a voice from just a few seconds of audio with F5-TTS, E2-TTS and CosyVoice. Fine-tuned model support included.基于 F5-TTS、E2-TTS 与 CosyVoice，仅需几秒音频即可克隆声音，同时支持微调模型。
Edge-TTS brings 400+ voices across 100+ languages; kokoro ranks #2 on the HuggingFace TTS Arena.Edge-TTS 提供覆盖 100+ 语言的 400+ 音色；kokoro 在 HuggingFace TTS Arena 排名第二。
One hub for YouTube downloads, noise removal, subtitles, translation and TTS — no need to juggle multiple tools.YouTube 下载、降噪、字幕、翻译与语音合成一站式集成，无需在多款工具间来回切换。
Everything runs locally. Your audio never leaves your computer — no cloud upload, no data collection.所有处理都在本地完成，音频数据绝不离开电脑——无云端上传、无数据采集。
Tauri 2 wrapper handles setup: dependencies and models download automatically on first launch, then the app opens itself.Tauri 2 封装自动完成环境配置：首次启动自动下载依赖与模型，随后直接打开应用界面。
Download: Grab the installer from GitHub Releases for macOS (Apple Silicon) or Windows (.exe).下载：从 GitHub Releases 获取对应平台安装包：macOS（Apple Silicon）或 Windows（.exe）。
First launch: The app prepares its environment and downloads required models automatically (a few minutes depending on your connection).首次启动：应用自动准备环境并下载所需模型（视网络情况约需几分钟）。
Create: Record or upload audio, pick a voice, and generate covers or speech in seconds.创作：录制或上传音频，选择音色，数秒内即可生成翻唱或语音。
Export: Download high-quality audio output, ready for your projects.导出：输出高品质音频文件，直接用于你的项目。