Converts messy voice-to-text and unstructured thoughts into clean, actionable structures for Claude.
The Voice Input Processor is a specialized pre-processing skill designed to bridge the gap between spontaneous verbal expression and structured task execution. It intelligently corrects phonetic voice-to-text errors, reorders non-linear thoughts, and extracts core intent without losing the nuance of the original input. By providing both a low-cognitive-load human summary and a detailed structured handoff for Claude, it ensures that 'thinking out loud' or rough dictations are accurately understood before any code is written or actions are taken, making it an essential tool for neurodivergent professionals and voice-driven workflows.
Key Features
01Intelligent phonetic correction for voice-to-text mishearings
020 GitHub stars
03Non-linear thought reordering into logical sequences
04Automatic trigger for long or messy inputs
05Dual-output generation: user-friendly summary and structured AI handoff
06Charitable interpretation of complex or incomplete sentences
Use Cases
01Cleaning up rough dictations and voice memos before starting a coding task
02Structuring brain dumps into logical project requirements
03Clarifying complex, multi-layered instructions provided via speech-to-text
