OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Voice Pro

Voice Pro is a Python and Gradio web application for multimedia audio processing, combining speech recognition, translation, text-to-speech, zero-shot voice cloning, YouTube downloading and vocal separation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Voice Pro — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a multimedia task needs several audio stages—such as transcription, translation, voice generation or vocal separation—within one self-hosted web interface.

Who it is for

  • Video creators preparing translated or dubbed versions of multimedia.
  • Podcasters and audiobook creators who need transcription or vocal separation.
  • Researchers and multilingual professionals processing speech and audio.

Documented uses

  • Transcribe speech from multimedia using Whisper-family recognition tools.
  • Translate recognized text, with the project describing support for more than 100 languages.
  • Generate speech from text using Edge-TTS or Kokoro, or use zero-shot voice-cloning models.
  • Download YouTube media, extract audio and separate vocals as part of an audio workflow.
Before you choose

Requirements & limits

The repository is public and specifies the GPL-3.0 license. The README describes Voice Pro as free and open source. First-run setup requires internet access to retrieve dependencies and models.

  • The application combines transcription, translation, speech generation, YouTube audio extraction and vocal separation in one Gradio interface.
  • The documented stack includes Whisper and Faster-Whisper, Deep-Translator, Edge-TTS, Kokoro, F5-TTS, E2-TTS, CosyVoice, yt-dlp and Demucs.
  • The Windows setup requires substantial storage: at least 20GB free, with model downloads estimated at about 10GB.
  • CPU use is documented, while the requirements also specify an NVIDIA GPU and VRAM guidance.
  • Mac and Linux setup scripts are mentioned, but the README says operation on those platforms has not been verified.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and launch Voice Pro on Windows

Set up the documented Windows environment and open the Voice Pro WebUI.

Before you start

  • Windows 10 or 11, 64-bit
  • Internet access
  • At least 20GB free storage and 4GB RAM
  • An NVIDIA GPU with 4GB or more VRAM is specified; CPU operation is also documented.

Steps

  1. Clone the repository or download the latest release source archive.

  2. Optionally run configure.bat once to set up Git and ffmpeg system-wide; this step requires administrator rights. If skipped, start.bat downloads portable ffmpeg.

  3. Run start.bat to launch the WebUI. On first run it downloads uv, Python 3.12, dependencies and AI models.

  4. If installation issues arise, delete installer_files and run start.bat again.

Expected outcome

The local Voice Pro WebUI launches after the environment and model downloads complete.

Guide limitations

  • The first run downloads about 10GB of AI models and requires internet access.
  • The README says Mac and Linux operation has not been verified.
  • The README says development and updates are paused.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
abus-aikorea/voice-pro · Official homepage title · retained in its source language
How we review sourcesSuggest a correction