Smart Subtitle

✅ One-click audio-to-subtitle conversion

• Uses locally deployed speech recognition engine to automatically convert audio into precisely timed subtitles
• Supports multiple languages (English, Chinese, Japanese, etc.), English and Chinese have been tested

✅ Efficient content creation

• Customizable text segmentation for optimal subtitle formatting
• Batch processing support to significantly improve workflow for cutscenes and dialogue systems

✅ Seamless Timeline integration

• Native Timeline editor support - no need for third-party software

Currently Supported Features

• Generates three subtitle track types: TextMeshProUGUI, TextMeshPro, and Legacy Text
• Customizable speech recognition models (requires manual model file downloads)
• Configurable speech recognition prompts
• Batch processing for multiple selections
• Subtitle delay adjustment
• Predefined punctuation rulesAutomatic line breaks based on:Maximum character length

Planned Features

• SRT export format
• Proofreading tools and interface
• Audio clip-level controls
• Post-generation adjustments