Speech-to-text input for Claude Code with live streaming dictation
Enables voice-to-text input in Claude Code using local speech recognition. Speak while holding a hotkey to transcribe audio directly into the editor.
Why this plugin
Offers privacy-focused, low-latency dictation processed entirely on-device. Solves the need for hands-free coding and accessibility without relying on external cloud services.
Prerequisites
Python 3.10-3.13, microphone access, ~200MB disk space for model. Platform-specific: macOS accessibility permissions, Linux xdotool, Windows pywin32.
npx claudepluginhub jarrodwatts/claude-sttExpert guidance for Next.js Cache Components and Partial Prerendering (PPR). Proactively activates in projects with cacheComponents: true, providing patterns for 'use cache' directive, cacheLife(), cacheTag(), cache invalidation, and parameter permutation rendering.
Migrate your code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5.
Persistent memory system for Claude Code - seamlessly preserve context across sessions
Error analysis, trace debugging, and multi-agent problem diagnosis