abus-aikorea / voice-pro

查看原文 / View Original 编辑 / Edit

Voice-Pro: The Best AI Speech Recognition, Translation, and Multilingual Dubbing Solution 🚀

Voice-Pro：最佳 AI 语音识别、翻译与多语言配音解决方案 🚀

🎙️ An AI-powered web application for speech recognition, translation, and dubbing. 한국어 ∙ English ∙ 中文简体 ∙ 中文繁體 ∙ 日本語 ∙ Deutsch ∙ Español ∙ Português

🎙️ 一款基于 AI 的语音识别、翻译与配音 Web 应用程序。 韩语 ∙ 英语 ∙ 简体中文 ∙ 繁体中文 ∙ 日语 ∙ 德语 ∙ 西班牙语 ∙ 葡萄牙语

Voice-Pro is a state-of-the-art web app that transforms multimedia content creation. It integrates YouTube video downloading, voice separation, speech recognition, translation, and text-to-speech into a single, powerful tool for creators, researchers, and multilingual professionals.

Voice-Pro 是一款改变多媒体内容创作方式的尖端 Web 应用。它将 YouTube 视频下载、人声分离、语音识别、翻译和文本转语音（TTS）集成到一个功能强大的工具中，专为创作者、研究人员和多语言专业人士打造。

🔊 Top-tier speech recognition: Whisper, Faster-Whisper, Whisper-Timestamped 🎤 Zero-shot voice cloning: F5-TTS, E2-TTS, CosyVoice (incl. Fun-CosyVoice3 — Korean and 8 more languages) 📢 Multilingual text-to-speech: Edge-TTS, kokoro (optional Azure TTS with your own keys — see Azure services) 🎥 YouTube processing & audio extraction: yt-dlp 🌍 Instant translation for 100+ languages: Deep-Translator (optional Azure Translator with your own keys)

🔊 顶级语音识别：Whisper, Faster-Whisper, Whisper-Timestamped 🎤 零样本语音克隆：F5-TTS, E2-TTS, CosyVoice（包含 Fun-CosyVoice3，支持韩语及其他 8 种语言） 📢 多语言文本转语音：Edge-TTS, kokoro（可选配 Azure TTS，需使用您自己的密钥 — 详见 Azure 服务） 🎥 YouTube 处理与音频提取：yt-dlp 🌍 100 多种语言即时翻译：Deep-Translator（可选配 Azure Translator，需使用您自己的密钥）

A robust alternative to ElevenLabs, Voice-Pro empowers podcasters, developers, and creators with advanced voice solutions.

作为 ElevenLabs 的强力替代方案，Voice-Pro 为播客主、开发者和创作者提供了先进的语音解决方案。

⚠️ Please Note: Due to WeConnect development work, Voice-Pro development and updates are not possible for the time being. We have made all Voice-Pro code open source and completely free. Voice-Pro can now be freely distributed and modified by anyone. It works well on Windows with NVIDIA GPU. Operation on Mac and Linux has not been verified. Please leave your requests on the [GitHub] or [Discord] pages.

⚠️ 请注意：由于 WeConnect 的开发工作，Voice-Pro 目前无法进行开发和更新。我们已将所有 Voice-Pro 代码开源并完全免费。现在任何人都可以自由分发和修改 Voice-Pro。它在配备 NVIDIA GPU 的 Windows 系统上运行良好。在 Mac 和 Linux 上的运行情况尚未验证。请在 [GitHub] 或 [Discord] 页面上提交您的需求。

Troubleshooting: In most cases, issues can be resolved by deleting the installer_files folder and then running start.bat again (a clean reinstall takes only a few minutes; downloaded AI models in model/ are kept). Errors are shown in the WebUI as red toasts that stay until closed.

故障排除：在大多数情况下，删除 installer_files 文件夹并重新运行 start.bat 即可解决问题（重新安装只需几分钟；model/ 文件夹中已下载的 AI 模型会被保留）。错误信息会以红色提示框的形式显示在 WebUI 中，直到手动关闭。

📰 News & History

📰 新闻与历史版本

version 4.0

⚡ Migrated the installer from Miniconda/pip to uv — dramatically faster, fully reproducible installs from a committed uv.lock. Everything stays inside installer_files/ (uv, Python, packages). 🐍 Upgraded runtime: Python 3.12, Torch 2.8.0+cu128 (RTX 50-series supported), Gradio 6.20. 🎙️ Latest ASR stack: faster-whisper 1.2.1 (large-v3-turbo, distil-large-v3.5), openai-whisper 20250625, whisper-timestamped 1.15.9. whisperX was removed (its dependency pins blocked the Gradio 6 upgrade; existing configs fall back to faster-whisper). 🗣️ Latest TTS stack: F5-TTS 1.1.21, kokoro 0.9.4, edge-tts 7.x, and re-vendored CosyVoice (upstream main). 🇰🇷 New optional TTS model: Fun-CosyVoice3-0.5B — 9 languages including Korean, selectable in the CosyVoice tab (downloads from the official HF repo on first use). 🧹 CUDA Toolkit and Visual Studio Build Tools are no longer required — all dependencies ship prebuilt wheels, and PyTorch bundles the CUDA runtime. 🛡️ Friendly to restricted / corporate PCs: no administrator rights needed — start.bat auto-downloads a portable ffmpeg if it is not installed, Whisper model downloads self-heal after interrupted/corrupted transfers, and translation automatically retries with backoff when the network rate-limits the free Google endpoint (failed lines are reported, originals kept). 🚨 Errors are now visible in the WebUI: every failure shows a red error toast that stays on screen until you close it (previously a 10-second warning that was easy to miss), with actionable messages for common causes (missing ffmpeg, no media registered, etc.). 🖥️ UI: migrated to Gradio 6 (full-width layout for all tabs, subtitle tracks shown directly in the video players). 🧽 uninstall.bat no longer requires administrator rights and no longer force-reboots; uninstall.bat silent runs unattended.

4.0 版本 ⚡ 将安装程序从 Miniconda/pip 迁移至 uv — 安装速度大幅提升，且通过 uv.lock 实现完全可复现的安装。所有内容均保留在 installer_files/ 目录内（uv、Python、包）。 🐍 升级运行环境：Python 3.12, Torch 2.8.0+cu128（支持 RTX 50 系列）, Gradio 6.20。 🎙️ 最新 ASR 栈：faster-whisper 1.2.1 (large-v3-turbo, distil-large-v3.5), openai-whisper 20250625, whisper-timestamped 1.15.9。移除了 whisperX（其依赖项限制阻碍了 Gradio 6 的升级；现有配置将回退至 faster-whisper）。 🗣️ 最新 TTS 栈：F5-TTS 1.1.21, kokoro 0.9.4, edge-tts 7.x，以及重新引入的 CosyVoice（上游主分支）。 🇰🇷 新增可选 TTS 模型：Fun-CosyVoice3-0.5B — 支持包括韩语在内的 9 种语言，可在 CosyVoice 选项卡中选择（首次使用时从官方 HF 仓库下载）。 🧹 不再需要 CUDA Toolkit 和 Visual Studio Build Tools — 所有依赖项均提供预构建的 wheel 包，且 PyTorch 已捆绑 CUDA 运行时。 🛡️ 对受限/公司电脑友好：无需管理员权限 — 若未安装 ffmpeg，start.bat 会自动下载便携版；Whisper 模型下载中断或损坏后可自动修复；当网络限制免费 Google 端点时，翻译功能会自动重试（报告失败行，保留原文）。 🚨 错误信息在 WebUI 中可见：每次失败都会显示一个红色错误提示框，直到手动关闭（此前为易被忽略的 10 秒警告），并提供针对常见原因（缺少 ffmpeg、未注册媒体等）的可操作建议。 🖥️ UI：迁移至 Gradio 6（所有选项卡采用全宽布局，字幕轨道直接显示在视频播放器中）。 🧽 uninstall.bat 不再需要管理员权限，也不再强制重启；uninstall.bat 可静默运行。

version 3.2

We have been focusing on WeConnect development for the past few months and have not been able to manage Voice-Pro at all. We have decided to open source all Voice-Pro code. Voice-Pro is completely free and supports Windows, Mac, Linux. WeConnect is an application for global cultural exchange. Connect with people from all over the world for meaningful cultural exchanges, language learning, and international friendships.

3.2 版本 过去几个月我们一直专注于 WeConnect 的开发，无暇顾及 Voice-Pro。我们决定将所有 Voice-Pro 代码开源。Voice-Pro 完全免费，支持 Windows、Mac 和 Linux。WeConnect 是一款全球文化交流应用，旨在与世界各地的人们建立联系，进行有意义的文化交流、语言学习和国际友谊。

version 3.1

🪄 Support for fine-tuned models of F5-TTS 🌍 Supported languages: English & Chinese (SWivid/F5-TTS_v1), Finnish (AsmoKoskinen/F5-TTS_Finnish_Model), French (RASPIAUDIO/F5-French-MixedSpeakers-reduced), Hindi (SPRINGLab/F5-Hindi-24KHz), Italian (alien79/F5-TTS-italian), Japanese (Jmica/F5TTS/JA_21999120), Russian (hotstone228/F5-TTS-Russian), Spanish (jpgallegoar/F5-Spanish).

3.1 版本 🪄 支持 F5-TTS 的微调模型。 🌍 支持语言：英语与中文 (SWivid/F5-TTS_v1)、芬兰语 (AsmoKoskinen/F5-TTS_Finnish_Model)、法语 (RASPIAUDIO/F5-French-MixedSpeakers-reduced)、印地语 (SPRINGLab/F5-Hindi-24KHz)、意大利语 (alien79/F5-TTS-italian)、日语 (Jmica/F5TTS/JA_21999120)、俄语 (hotstone228/F5-TTS-Russian)、西班牙语 (jpgallegoar/F5-Spanish)。

version 3.0

🔥 Removed the AI Cover feature. 🚀 Added support for m-bain/whisperX.

3.0 版本 🔥 移除了 AI 翻唱功能。 🚀 增加了对 m-bain/whisperX 的支持。

version 2.0

🐍 Built with Python 3.10.15, Torch 2.5.1+cu124, and Gradio 5.14.0. 🆓 Free trial supports media up to 60 seconds in length. 🔥 Added the AI Cover feature. 🎤 Introduced support for CosyVoice and kokoro. ⏳ Initial run downloads CozyVoice2-0.5B (9GB), which may take over an hour depending on network speed. 🎧 Voice samples for cloning will be continuously updated. 📝 Added spaCy for natural sentence-by-sentence translation and TTS. ☁️ Subscription version includes Microsoft Azure Translator and TTS. 🏪 Subscription offers unlimited usage (no 60-second limit) during the subscription period.

2.0 版本 🐍 基于 Python 3.10.15, Torch 2.5.1+cu124 和 Gradio 5.14.0 构建。 🆓 免费试用支持最长 60 秒的媒体文件。 🔥 增加了 AI 翻唱功能。 🎤 引入了对 CosyVoice 和 kokoro 的支持。 ⏳ 首次运行需下载 CozyVoice2-0.5B (9GB)，根据网速可能需要一小时以上。 🎧 用于克隆的语音样本将持续更新。 📝 加入 spaCy 以实现自然的逐句翻译和 TTS。 ☁️ 订阅版本包含 Microsoft Azure 翻译和 TTS。 🏪 订阅期内提供无限使用权限（无 60 秒限制）。

⭐ Key Features

⭐ 核心功能

  1. Dubbing Studio
    • YouTube video downloads & audio extraction
    • Voice separation with Demucs
    • Supports 100+ languages for speech recognition & translation

1. 配音工作室 (Dubbing Studio) - YouTube 视频下载与音频提取 - 使用 Demucs 进行人声分离 - 支持 100 多种语言的语音识别与翻译

  1. Speech Technologies
    • Speech-to-Text: Whisper, Faster-Whisper, Whisper-Timestamped
    • Text-to-Speech: Edge-TTS (100+ languages, 400+ voices), E2-TTS, F5-TTS, CosyVoice (Zero-shot cloning), kokoro (Ranked #2 in HuggingFace TTS Arena)

2. 语音技术 - 语音转文字：Whisper, Faster-Whisper, Whisper-Timestamped - 文本转语音：Edge-TTS（100 多种语言，400 多种音色）、E2-TTS、F5-TTS、CosyVoice（零样本克隆）、kokoro（HuggingFace TTS 竞技场排名第二）

  1. Real-Time Translation
    • Instant speech recognition
    • Multilingual translation on the fly
    • Customizable audio inputs

3. 实时翻译 - 即时语音识别 - 动态多语言翻译 - 可自定义音频输入

🤖 WebUI Dubbing Studio Tab

🤖 WebUI 配音工作室选项卡

← 返回新闻列表 / Back to news list