ChatGPT's Live Video voice quietly switches you to GPT-4o, barely documented
RileyRalmuto · x · 2026-10-21
RileyRalmuto highlights a little-known detail: using Live Video voice in ChatGPT switches the model to GPT-4o, and the Advanced Voice Model (AVM) is also 4o underneath. Screenshots show an in-app prompt to switch voice models for Live Video, with the model self-identifying as the current GPT-4o. The author argues that absent a secret unreleased omni model, 4o remains OpenAI's only true end-to-end omni model trained jointly on sound, sight, and language — it genuinely hears you rather than transcribing first. The swap is barely documented and only accessible via the Live Video flow or by setting AVM as primary.
More from Models
- Uncensored DeepSeek V4.1 Flash GGUFs drop refusal rate from 91.4% to 0% with minimal MMLU loss — kalyan_kpl · 2026-10-21
- Meta engineer confirms Google TPUs now run AI inference in Meta production — dotey · 2026-10-21
- Don't mention recent AI math results to Opus 5.5 if you want it to focus — repligate · 2026-10-21
- User finds codex now beats ChatGPT for everything but quick phone searches — verrsane · 2026-10-21
- Nace.AI Launches Drex Max 2.0, a 27B Local Decision Model for Computer Use — DotaMate · 2026-10-21
- Speculation: Codex/Work also cap at 12 hours — OpenAI quietly eats cache-miss costs — dotey · 2026-10-21