Voice Pro

<!-- title: Voice-Pro: Ultimate AI Voice Conversion and Multilingual Translation Tool description: Powerful AI-powered web application for YouTube video processing, speech recognition, translation, and text-to-speech with multilingual support keywords: AI voice conversion, YouTube translation, subtitle generation, speech-to-text, text-to-speech, voice cloning, multilingual translation, ElevenLabs Alternative author: ABUS version: 4.0.0 last-updated: 2026-07-13 product-type: AI Multimedia Processing Software platforms: Windows technology-stack: Whisper, Edge-TTS, Gradio, CUDA, Faster-Whisper, Whisper-Timestamped, E2-TTS, F5-TTS, YouTube Downloader, Demucs, MDX-Net, CosyVoice, kokoro, uv license: LGPL --> <h1 align="center"> Voice-Pro </h1> <p align="center"> <i align="center">The best AI speech recognition, translation, and multilingual dubbing solution 🚀</i> </p> <h4 align="center"> <a href="https://deepwiki.com/abus-aikorea/voice-pro"> <img alt="Ask DeepWiki.com" src="https://deepwiki.com/badge.svg" style="height: 20px;"> </a> <a href="https://www.youtube.com/channel/UCbCBWXuVbk-OBp9T4H5JjAA"> <img src="https://img.shields.io/badge/youtube-d95652.svg?style=flat-square&logo=youtube" alt="youtube" style="height: 20px;"> </a> <a href="https://www.buymeacoffee.com/abus"> <img src="https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png" alt="Buy Me a Coffee" style="height: 20px;"> </a> <a href="https://github.com/abus-aikorea/voice-pro/releases"> <img src="https://img.shields.io/github/v/release/abus-aikorea/voice-pro" alt="release" style="height: 20px;"> </a> <a href="https://github.com/abus-aikorea/voice-pro/stargazers"> <img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/abus-aikorea/voice-pro"> </a> </h4> <p align="center"> <img src="docs/images/main_page_crop.eng.jpg?raw=true" alt="Dubbing Studio"/> </p> <br />

🎙️ An AI-powered web application for speech recognition, translation, and dubbing

<p> <a href="docs/README.kor.md"> <img src="https://flagcdn.com/16x12/kr.png" alt="South Korea Flag" style="vertical-align: middle;"> 한국어 </a> ∙ <a href="docs/README.eng.md"> <img src="https://flagcdn.com/16x12/us.png" alt="United Kingdom Flag" style="vertical-align: middle;"> English </a> ∙ <a href="docs/README.zh.md"> <img src="https://flagcdn.com/16x12/cn.png" alt="China Flag" style="vertical-align: middle;"> 中文简体 </a> ∙ <a href="docs/README.tw.md"> <img src="https://flagcdn.com/16x12/tw.png" alt="Taiwan Flag" style="vertical-align: middle;"> 中文繁體 </a> ∙ <a href="docs/README.jpn.md"> <img src="https://flagcdn.com/16x12/jp.png" alt="Japan Flag" style="vertical-align: middle;"> 日本語 </a> ∙ <a href="docs/README.deu.md"> <img src="https://flagcdn.com/16x12/de.png" alt="Germany Flag" style="vertical-align: middle;"> Deutsch </a> ∙ <a href="docs/README.spa.md"> <img src="https://flagcdn.com/16x12/es.png" alt="Spain Flag" style="vertical-align: middle;"> Español </a> ∙ <a href="docs/README.por.md"> <img src="https://flagcdn.com/16x12/pt.png" alt="Portugal Flag" style="vertical-align: middle;"> Português </a> </p>

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.

• 🔊 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)

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

⚠️ 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 or pages.
• 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.

📰 News & History

<details open> <summary>version 4.0</summary>

• ⚡ 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.

</details> <details> <summary>version 3.2</summary>

• 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.

<p align="center"> <img src="docs/images/Hotpot 0.png?raw=true" alt="ScreenShot 0" width="18%"/> <img src="docs/images/Hotpot 1.png?raw=true" alt="ScreenShot 1" width="18%"/> <img src="docs/images/Hotpot 2.png?raw=true" alt="ScreenShot 2" width="18%"/> <img src="docs/images/Hotpot 3.png?raw=true" alt="ScreenShot 3" width="18%"/> <img src="docs/images/Hotpot 4.png?raw=true" alt="ScreenShot 4" width="18%"/> </p> </details> <details> <summary>version 3.1</summary>

• 🪄 Support for fine-tuned models of F5-TTS
• 🌍 Supported languages
  • <img src="https://flagcdn.com/16x12/us.png" alt="United Kingdom Flag" style="vertical-align: middle;"> English & <img src="https://flagcdn.com/16x12/cn.png" alt="China Flag" style="vertical-align: middle;"> Chinese: <a href="https://huggingface.co/SWivid/F5-TTS/tree/main/F5TTS_v1_Base"> SWivid/F5-TTS_v1 </a>
  • <img src="https://flagcdn.com/16x12/fi.png" alt="Spain Flag" style="vertical-align: middle;"> Finnish: <a href="https://huggingface.co/AsmoKoskinen/F5-TTS_Finnish_Model"> AsmoKoskinen/F5-TTS_Finnish_Model </a>
  • <img src="https://flagcdn.com/16x12/fr.png" alt="Spain Flag" style="vertical-align: middle;"> French: <a href="https://huggingface.co/RASPIAUDIO/F5-French-MixedSpeakers-reduced"> RASPIAUDIO/F5-French-MixedSpeakers-reduced </a>
  • <img src="https://flagcdn.com/16x12/in.png" alt="Spain Flag" style="vertical-align: middle;"> Hindi: <a href="https://huggingface.co/SPRINGLab/F5-Hindi-24KHz"> SPRINGLab/F5-Hindi-24KHz </a>
  • <img src="https://flagcdn.com/16x12/it.png" alt="Spain Flag" style="vertical-align: middle;"> Italian: <a href="https://huggingface.co/alien79/F5-TTS-italian"> alien79/F5-TTS-italian </a>
  • <img src="https://flagcdn.com/16x12/jp.png" alt="Spain Flag" style="vertical-align: middle;"> Japanese: <a href="https://huggingface.co/Jmica/F5TTS/tree/main/JA_21999120"> Jmica/F5TTS/JA_21999120 </a>
  • <img src="https://flagcdn.com/16x12/ru.png" alt="Spain Flag" style="vertical-align: middle;"> Russian: <a href="https://huggingface.co/hotstone228/F5-TTS-Russian"> hotstone228/F5-TTS-Russian </a>
  • <img src="https://flagcdn.com/16x12/es.png" alt="Spain Flag" style="vertical-align: middle;"> S