Skip to content

Changelog

v1.0.0-beta Current

First public Beta release with the full core workflow available.

Core features

Media import

  • Paste YouTube/web video links for automatic downloading (via yt-dlp)
  • Drag and drop local video/audio files (MP4, MP3, AAC, M4A, etc.)
  • Auto-extract title, thumbnail, duration, and source metadata

AI transcription

  • Multi-language speech recognition with automatic language detection
  • Segment-level timeline alignment with editable corrections

Translation

  • Dual engines: DeepSeek API / Microsoft Translator
  • Segment-level translation with bilingual side-by-side display
  • Batch translation with configurable concurrency (1–20)

AI summaries

  • Generate summaries, tags, and key timeline points
  • Custom prompts supported for flexible output structure

Moment collection

  • One-click highlight to save important segments
  • Automatic screenshot archiving, organized by collections

Search & navigation

  • Full-text search through transcript content and jump to exact timestamps

Export

  • Export subtitles in SRT / VTT formats
  • Export Markdown (including summary)
  • MP4 export with subtitles: burned-in captions, up to 4K, watermark, bilingual subtitle mode

Others

  • Soft delete (trash) and restore projects
  • Complete settings panels (transcription, translation, LLM, TTS, proxy, prompts)
  • Supports macOS (Apple Silicon + Intel), Windows (x64 + ARM64)

Have a feature request or found a bug? Open an issue in GitHub Issues.

Beta is fully free right now. Commercial plans are in progress.