Using TTS for completion notifications caused cognitive overload
brandon_galang · x · 2026-08-31
The author shared a failed attempt to upgrade their AI coding workflow's audio feedback. Initially using a simple "Odyssey bow pluck" sound for agent completions, they switched to using the Cartesia Sonic 3.5 voice model to verbally announce which session had finished (e.g., "Codex has finished in session...").
Outcome & Lesson:
- In practice, frequent overlapping voice announcements created overwhelming noise and cognitive load.
- Conclusion: Non-verbal audio cues are superior for high-frequency notifications; not every technical upgrade results in a better UX.
More from coding & agent
- Built a RAG app that cites course timestamps and quotes — Al_Grigor · 2026-08-31
- Swyx breaks down pre-training vs post-training and what's holding back agents — iamrobotbear · 2026-08-31
- Using Codex with Blender beats hiring a 3D modeler for speed — natesiggard · 2026-08-31
- Exploring Object Detection Prompt Optimization for LLMs in DSPy — lateinteraction · 2026-08-31
- Report: OpenAI bought tens of thousands of Mac minis for agent training — ZeroStateReflex · 2026-08-31
- Meta^n: Recursive Self-Improvement Hits 0.331 on ARC-AGI-2 — burny_tech · 2026-08-31