Goals

Active

• Create voice-to-structured-data CLI #high
• Multi-provider support (Claude, Codex, Gemini) #high
• Improve transcription accuracy #medium
• Add support for longer recordings #medium
• Better field extraction with custom criteria #medium
• Docker containerization for easy deployment #high

Future

• Real-time transcription mode
• Custom vocabulary support
• Integration with more applications
• Voice command mode
• Stability AI image generation integration
• Pexels image search integration

Non-Goals

• Replacing full dictation software - Ramble focuses on structured extraction, not general transcription
• Standalone transcription service - It's a tool for developers, not an end-user service