capture-voice-idea

name	capture-voice-idea
description	Capture a business idea from a voice memo / audio file. Transcribes the recording, preserves the raw transcript, then hands off to capture-idea so the user can optionally generate executive summary, elevator pitch, technical deep-dive, and timeline variants. Use when the user has an audio file or recording of an idea pitch.

Capture Idea (voice)

Pipeline: audio → transcript → structured idea workspace.

Steps

1. Resolve config (workspace path, user context).
2. Take the audio file path from the user. Verify it exists and looks like an audio file.
3. Transcribe. Prefer the claude-transcription plugin's skills if installed:
   • claude-transcription:transcribe-gemini-cleaned — fastest path, removes filler words
   • claude-transcription:transcribe-gemini-raw — verbatim if the user wants every word preserved
   • Fallback: prompt the user to install claude-transcription or supply an existing transcript.
4. Save the raw transcript to a temp path. Show the user a short preview (first ~200 words) before proceeding.
5. Hand the transcript to capture-idea:
   • Pass the transcript text as the raw input
   • Tag the resulting idea.md frontmatter with source: voice and audio_file: <original-path>
   • Copy the audio file (or symlink) into <workspace_path>/ideas/<idea-slug>/source-audio.<ext> so the recording stays with the workspace
6. Continue through capture-idea's formatted-variant menu so the user can pick which derived versions to generate.

Notes

• Voice captures often contain digressions and false starts. Prefer the cleaned transcription unless the user explicitly wants raw.
• For long recordings (>30 min), suggest claude-transcription:truncate-silence first.
• Always preserve the original audio file in the workspace — it's the ultimate source.