I Built a Recipe Book for My Dadi, Using AI That Never Leaves My Laptop

Developer Vidisha Gupta has created 'Dadi ki Rasoi,' a local-first application designed to preserve family recipes by transcribing voice notes into structured, printable cookbooks. Utilizing open-source tools like faster-whisper for transcription and Ollama for local LLM processing, the project ensures that sensitive family audio data remains entirely on the user's laptop, bypassing cloud-based privacy concerns. The application handles Hinglish, converts traditional, imprecise measurements into standardized quantities, and preserves cultural nuances by keeping original anecdotes intact. By opting for a local-first architecture, Gupta demonstrates the practical advantages of open-source AI, including offline functionality, cost-efficiency, and the ability to compare different models for better accuracy. The project, which is available on GitHub, highlights how local AI can serve personal, sentimental purposes while maintaining strict data sovereignty and control over the creative output.
This is a summary. Read the full article at the original source:
Dev.toRelated stories
AI Photoshoots from Photos: Top Services in 2026 and Ready-to-Use Prompts
This article examines modern methods for creating AI photoshoots based on user photos. The author highlights two main approaches: automatic generation…
How I automated Threads management with an AI agent: 188 posts and comment replies for $4–6 per month
The creator of the EverStory project shared her experience in automating a Threads social media account using a custom AI agent named Amy. The solutio…
The Witness Was the Suspect: Why AI Audit Logs Can't Be Trusted
In AI-driven systems, the traditional reliance on audit logs is fundamentally flawed because the agent performing an action is often the same entity r…



