Show HN: Speech to Calorie Tracker (github.com)

A new voice-powered diet tracker application has been introduced, built for iPhone using vanilla HTML and JavaScript, harnessing the capabilities of Claude AI. Users can log their meals simply by speaking about what they've eaten, with Claude converting these descriptions into a structured nutrition table that includes calories, protein, carbs, fat, and fiber. A unique feature of the app is the MCP server, allowing users to interact with Claude Desktop for personalized dietary advice based on their logged meals. The app operates as a Progressive Web App (PWA), ensuring offline functionality and data privacy by storing all user data directly in the browser without relying on a backend server. This innovation is significant for the AI/ML community as it demonstrates the versatile applications of generative AI in personal health and wellness. Technical highlights include the use of the Web Speech API for voice recognition, a local storage approach for personal data protection, and seamless integration with the Anthropic Claude API, which enhances meal logging accuracy. The app's design prioritizes user experience, making it easy to track food intake without needing complex setups or external server dependencies, ultimately encouraging healthier eating habits through intuitive technology.