- texan profile pitch/rate adjusted (0.65/0.75) to differentiate from deep (0.7/0.7) - Audited all 60 voice profiles: no remaining pitch+rate duplicates - Category announces verified: all fire correctly via speak() pipeline - Speech queue already capped at depth 2 with cancel, no debounce needed - TTS fallback already graceful: speak() returns silently when unavailable Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>