abus-aikorea/voice-pro
Voice Pro
Voice Pro is a comprehensive speech and audio processing toolkit that combines text-to-speech synthesis, voice cloning, speech recognition, and translation capabilities into a single application. At its core, the project enables users to generate natural-sounding speech from text, clone voices from short audio samples without requiring prior training data, and perform real-time speech translation across over 100 languages.
The platform distinguishes itself through its integrated multimedia workflow, allowing users to download YouTube videos, extract audio, separate voice tracks, generate word-timed subtitles, and produce dubbed content in over 100 languages through a unified pipeline. It supports multiple speech synthesis engines including Edge-TTS, F5-TTS, E2-TTS, CosyVoice, and kokoro, while also providing the ability to train custom TTS models on user-provided datasets and export trained models to ONNX format for deployment.
Beyond core speech generation, the application offers extensive audio processing features such as transcribing speech to text with word-level subtitle generation, translating subtitle files while preserving formatting, and performing real-time speech recognition and translation with customizable audio inputs. The system also includes capabilities for extracting audio from video, removing noise, and managing the application's installation and dependencies through built-in cleanup utilities.
Features
- AI Video Dubbing Tools - Provides an integrated AI dubbing pipeline that downloads, transcribes, translates, and dubs videos.
- Subtitle Translation - Converts subtitle files (ASS, SSA, SRT) into over 100 languages while preserving timing and formatting.
- Multilingual Voice Cloning Synthesizers - Generates speech using multiple cloning engines with support for celebrity voices and multilingual output.
- Zero-Shot Voice Cloning - Provides zero-shot voice cloning from short audio samples without additional training.
- Real-Time Speech Translation - Recognizes speech and translates it into multiple languages in real time.
- Speech-to-Text Engines - Converts spoken audio from files or streams into text using multiple recognition engines.
- Automated Video Subtitling - Transcribes audio to word-level subtitles with noise removal and multilingual support.
- Text-to-Speech - Generates natural-sounding speech from text using conditional flow matching synthesis.
- Speech Synthesis & TTS - Converts text to speech using multiple engines with support for 100+ languages and 400+ voices.
- ONNX Model Exporters - Exports trained TTS checkpoints to the ONNX format for cross-engine deployment.
- ONNX Runtime Inference - Runs speech synthesis inference on exported ONNX graphs with GPU acceleration.
- Custom TTS Model Training Pipelines - Trains custom TTS models on user-provided datasets with file list preparation and normalization.
- Word-Highlighted Subtitle Players - Ships a video player that displays word-highlighted subtitles with noise removal and multilingual support.
- Timestamped Subtitle Generators - Generates subtitle files with word-level timestamps from audio input.
- Audio Track Extraction - Extracts audio tracks from downloaded YouTube videos in multiple formats.
Star history
How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
