Skip to main content

Milestones

Active​

M1: Improved Accuracy​

Target: February 2026 Status: In Progress

Focus on improving transcription and extraction accuracy, with better error handling and support for longer recordings.

Key Deliverables:

  • Field locking persistence across sessions
  • Export to multiple formats (Markdown, YAML)
  • Keyboard shortcuts for common actions
  • Field validation with user-friendly error messages

M2: Extended Capabilities​

Target: Q2 2026 Status: Not Started

Expand Ramble with real-time transcription, custom vocabulary support, and voice command capabilities.

Key Deliverables:

  • Template system for common field configurations
  • History/recall of previous rambles
  • Voice input option (speech-to-text)
  • Comparison view for before/after extraction
  • Batch processing mode

Future​

M3: Integrations​

Target: Q3 2026 Status: Not Started

Integrate Ramble with external applications including Development Hub, Artifact Editor, and third-party tools.

Key Deliverables:

  • Browser extension for quick rambles
  • Mobile companion app
  • Collaborative rambling (shared sessions)
  • Integration with note-taking apps (Obsidian, Notion)

Completed​

M0: Core CLI​

Target: December 2025 Status: Complete

Delivered the foundational voice-to-structured-data CLI with Whisper transcription, AI-powered field extraction, multiple output formats, and template system.

Delivered:

  • Core extraction engine
  • PySide6 GUI implementation
  • PlantUML diagram generation
  • Headless CLI mode
  • Programmatic API
  • Field locking mechanism
  • Multi-provider support (Claude, Codex, Gemini)
  • Docker containerization