Skip to content

Releases: tylerbcrawford/subgeneratorr

Subgeneratorr v2.0.0

10 Mar 01:24
@tylerbcrawford tylerbcrawford
v2.0.0
d505bb5

Choose a tag to compare

View all tags
Subgeneratorr v2.0.0 Latest
Latest

Initial public release.

Added

  • Core Transcription Engine — Deepgram Nova-3 speech recognition with SRT subtitle output
  • Nova-3 Full Feature Coverage — Model selector (General/Medical), redaction (PCI/PII/numbers), find & replace, dictation mode, multichannel processing, utterance split threshold (0.1–5.0s), and request tagging
  • Audio Intelligence — Sentiment analysis, summarization, topic/intent/entity detection, and term search (English only, saved to Intelligence/ folder)
  • Web UI — Flask-based interface with dark/light themes, zone-based layout, gear popover for preferences, and collapsible Transcription Settings panel
  • CLI — Command-line tool for batch processing directories, individual files, or file lists
  • LLM-Enhanced Keyterms — Optional AI-powered generation of character names and terminology using Claude, GPT, or Gemini to improve transcription accuracy
  • Multi-Language Support — 50+ languages with regional variants
  • Multilingual Model — Special multi mode processes 10 languages simultaneously with automatic language detection
  • Language-Aware Audio Selection — Automatically selects the correct audio track in multi-language containers with surround sound center channel extraction
  • Speaker Diarization — Identify and label speakers in generated transcripts
  • Subtitle Detection — Sidecar file glob with ffprobe fallback to identify existing subtitles before processing
  • File Browser — Navigate media directories with client-side filtering and API-backed global search
  • Batch Processing — Queue multiple files with Celery/Redis, real-time progress tracking, and polling watchdog
  • Cost Tracking — Real-time per-file and session cost estimates (~$0.0043/min)
  • Docker Deployment — Docker Compose with multi-arch (amd64 + arm64) pre-built images via GitHub Actions
  • Media Server Integration — Output .eng.srt files auto-recognized by Plex, Jellyfin, and Emby
  • Documentation — Setup guide, technical reference, language support guide, API docs, contributing guidelines, and community files

Security

  • Path traversal protection — Input validation on file paths to prevent directory escape
  • Error path hardening — Removed bare excepts, added timeout guards, and safe handling of empty API responses
Assets 2
Loading