Skip to content

megaease/easevoice-trainer-portal

Folders and files

NameName
Last commit message
Last commit date
Mar 4, 2025
Mar 6, 2025
Mar 6, 2025
Jan 15, 2025
Feb 24, 2025
Feb 13, 2025
Jan 2, 2025
Jan 2, 2025
Feb 27, 2025
Mar 4, 2025
Mar 4, 2025
Jan 2, 2025
Feb 21, 2025
Mar 6, 2025
Jan 15, 2025
Mar 5, 2025
Mar 5, 2025
Jan 2, 2025
Feb 8, 2025
Jan 16, 2025
Jan 2, 2025
Jan 2, 2025
Feb 25, 2025

Repository files navigation

EaseVoice Trainer Portal

License 中文文档

The EaseVoice Trainer Portal is the front-end interface for EaseVoice Trainer and is designed to provide an intuitive and easy-to-use user interface for sound synthesis and conversion. This front-end project works in conjunction with the back-end of EaseVoice Trainer to make advanced sound cloning technology easy to users of all technology levels.

🔗 Backend Repository: EaseVoice Trainer Backend

✨ Features

  • 🎙️ Voice Cloning - Clone voices with high quality and natural sound
  • 🔊 Audio Processing - Record, upload and process audio files
  • 📊 Waveform Visualization - Visualize audio waveforms in real-time
  • 🤖 Model Training - Train and fine-tune AI voice models
  • ☁️ Cloud Storage - Manage your audio files and models in the cloud
  • 📝 Data Annotation - Annotate and manage training data

📸 Screenshots

voice-clone easy-mode advanced-mode

🛠️ Tech Stack

🚀 Getting Started

  1. Install dependencies:
pnpm install
  1. Create a development environment configuration file:
echo "VITE_API_BASE_URL=http://localhost:8000/apis/v1" > .env.development
  1. Start the development server:
pnpm dev
  1. Build for production:
pnpm build

📄 License

EaseVoice Trainer Portal is open-sourced under the Apache 2.0 License. See the LICENSE file for details.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published