🎬 What is CreatorBox?

CreatorBox is designed for creators, focusing on solving repetitive tasks in content creation workflows such as video translation, cross-language dubbing, and personalized dubbing. Simply provide the materials, and it will automatically complete speech recognition, translation, synthesis, and draft export, enhancing creation efficiency and unleashing creative potential!

📦 Quick Start

👉 Refer to the usage guide: Local Installation | Remote Deployment

CreatorBox, designed for creators, enhances creation efficiency and unleashes creative potential.

📺 Video Demonstration

🎨 What Can It Do?

• 🎥 Content Creators: Optimize video dubbing, translation, and editing workflows, enhancing creation efficiency and unleashing creative potential.

• 🌍 Multilingual Translation/Dubbing: Operate localized content creation and cross-language publishing.

• ⚙️ Independent Deployment: Deploy locally with flexible configurations to ensure privacy.

🎯 Features

• 🎤 Speech Recognition

  Accurately transcribe voices from videos and audio, with flexible configuration adjustments to suit different devices and scenarios, ensuring high-quality text generation.

• 🌐 Language Translation

  Translate between multiple languages, allowing switching of translation providers and adjustment of advanced parameters to optimize translation results and easily overcome language barriers.

• 🎧 Speech Synthesis

  A rich library of voices and customization options provide a personalized dubbing experience to meet creative needs, with real-time preview ensuring precise creation.

• ✂️ Draft Export

  Supports exporting materials to editing tools, offering fine-grained control over visuals, audio, and subtitles, aiding post-production adjustments and customization.

• 📤 Scene Modes

  Switch between various creation modes at any time, supporting video dubbing, translation, narration, and other scenarios to meet diverse user needs.

• 🔧 Preview and Debugging

  Provides flexible and efficient configuration adjustments to ensure perfect presentation at every stage, enhancing creation efficiency and quality.

📅 Planned Support

Recognition

• Support for video download, separation, and noise reduction.
• Support for audio and video transcription and subtitle loading.
• Support for speaker , voiceprint alignment.

Speech

• Support for multilingual speech synthesis with adjustable speed and preview.
• Support for voice cloning with three built-in tone types: default, video, and custom, all managed in a unified system.
• Support for voice commands, including built-in regional accents, speaking styles, and role-playing instructions.
• Support for voice tone conversion, enabling the transformation of a speaker's tone in an existing audio file to match the target speaker's tone.

Modes

• Support for video, audio, and adaptive 3 types of dubbing align modes
• Support for translation mode: Translate videos from the original language to another language.
• Support for narration mode (planned).

Draft

• Track Control: Support for controlling up to 6 tracks, including visuals, audio, and subtitles.
• Subtitle Generation: Support for font settings such as size, position, color, and outline.
• Volume Adjustment: Support for adjusting the volume of original sound, speech, and background music.
• Background Music: Random or specified music files.
• Transition Control: For use with long videos.

Debugging

• Configuration adjustments for subtitles, speakers, translation, and dubbing.

Others

• Support for long videos.
• Automated publishing and submission.