Voice-Pro

Voice-Pro is an open-source web app for speech recognition, translation, voice cloning and dubbing, built on Whisper and F5-TTS.

Voice-Pro is an open-source Gradio web app that combines the steps of dubbing a video. It downloads YouTube videos with yt-dlp, separates vocals from background audio, and transcribes speech with Whisper, Faster-Whisper or Whisper-Timestamped. Transcripts can be translated into more than 100 languages and spoken again with Edge-TTS, Kokoro or zero-shot voice cloning through F5-TTS, E2-TTS and CosyVoice. It runs on a Windows PC with an NVIDIA GPU, installs without administrator rights, and can optionally use Azure speech and translation with the user's own keys. The developers have paused updates while they work on another product, but all of the code is free to use and modify.

Voice-Pro at a glance

Best for: Social media creator, Writer
Runs on: Windows, self-hosted, open source
Pricing: Free and open source
Released: July 2024
Category: AI audio tool
Website: github.com/abus-aikorea/voice-pro

Key features

Speech recognition with Whisper, Faster-Whisper and Whisper-Timestamped
Zero-shot voice cloning with F5-TTS, E2-TTS and CosyVoice
Text to speech with Edge-TTS and Kokoro
Translation into 100+ languages
YouTube download and vocal separation
Windows installer that needs no administrator rights

Use it for

Dub a YouTube video into another language in a cloned voice
Make subtitles from a talk or podcast
Separate vocals from music for editing

Alternatives to Voice-Pro

VoiceStudio — Runs locally on your machine with no account, cloud connection, or API keys required.
Voicebox — Perform voice cloning and generation entirely on local hardware.
Fish Audio — Provides studio-grade voice cloning and text-to-speech with emotion control.
Scriber Pro 2.0 — Transcribes 4.5 hours of audio in 3.5 minutes completely offline.
VoxCPM — Provides tokenizer-free multilingual speech with controllable voice creativity.
Faster Whisper GUI — Provides a visual interface for faster-whisper, whisperX, and Demucs models.
MOSS-TTS — Delivers zero-shot voice cloning and fine-grained pronunciation control.
Whisper Diarization — Combines OpenAI Whisper with voice activity detection and speaker embedding.
TTS WebUI — It offers a free web interface with over 30 AI models for audio generation.
GPT-SoVITS — It allows high-fidelity voice cloning with as little as one minute of data.
Dub Anything — Runs locally on your PC and uses an AI coding agent to direct the dub line by line.
ElevenLabs — Natural AI voices, with 10,000+ voices in 70+ languages

All Voice-Pro alternatives