Claude STT enables hands-free text input via speech for Claude Code. Operations teams benefit from faster documentation and note-taking. Works with local processing for privacy. Integrates with Claude Code workflows.
git clone https://github.com/jarrodwatts/claude-stt.gitClaude STT enables hands-free text input via speech for Claude Code. Operations teams benefit from faster documentation and note-taking. Works with local processing for privacy. Integrates with Claude Code workflows.
["Install the Claude STT extension for your IDE (VS Code, Cursor, etc.) and ensure it's configured for local processing.","Start a Claude Code session and enable STT with the command: `claude-stt --enable --target-file [TARGET_FILE_PATH]` (e.g., `claude-stt --enable --target-file ./notes.md`).","Begin speaking your notes aloud while working. The STT will automatically transcribe and append your spoken notes to the target file with timestamps.","Review the transcribed notes in the target file and make any necessary corrections using your IDE's built-in tools.","Use the timestamped format to quickly search and reference specific parts of your workflow later. For example, search for `--- 2024-05-15 14:32:18 ---` to jump back to the API timeout debugging session."]
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/jarrodwatts/claude-sttCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Enable hands-free documentation for [TASK_NAME] using Claude STT. Speak your notes aloud while performing [TASK_NAME], and have the transcription automatically inserted into [TARGET_FILE] in the format: '--- [TIMESTAMP] --- [SPOKEN_NOTES]'. Ensure the transcription is timestamped and formatted for easy reference later.
--- 2024-05-15 14:32:18 --- Debugged the API timeout issue in the user service. The problem was in the retry logic in `services/user.js` line 47. Added a 3-second delay between retries and increased the max retry count from 3 to 5. Tested with Postman and confirmed the endpoint now responds within 2 seconds under load. Need to update the documentation in `docs/api.md` to reflect this change.
--- 2024-05-15 14:35:02 --- Fixed the memory leak in the batch processing job. The issue was in `jobs/batch_processor.js` where the event listener wasn't being removed after each batch. Added `batchEmitter.off('complete', cleanup)` in the cleanup function. Verified with `node --inspect` that memory usage stabilizes after processing 10,000 records. Ready to deploy to staging.
--- 2024-05-15 14:38:45 --- Updated the database schema for the new analytics tables. Ran `npx prisma migrate dev --name add_analytics_tables` and verified the migration in `prisma/schema.prisma`. The tables are now in sync with the application code. Waiting on DBA approval before merging to main.AI assistant built for thoughtful, nuanced conversation
Accurate AI voice transcription for sales teams
We’ve typed for 150 years. It’s time to speak.
All-in-one AI voice creation platform
Transform text into professional voiceovers instantly
AI voice generation for professional marketing content
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan