La nueva VOZ de ChatGPT + Codex es una LOCURA (5 casos reales)
ChatGPT's new voice mode integrated with Codex enables hands-free AI agent control for complex tasks like email management, app development, and automated scheduling. Users can now direct AI agents to execute work on their computer, manage multiple parallel tasks, and control operations remotely from mobile devices using only voice commands.
Summary
The transcript demonstrates ChatGPT's updated voice mode functionality within Codex, which operates as a real-time conversational agent rather than simple voice-to-text dictation. The host showcases five practical use cases. First, voice mode enables email management where the AI locates pending collaboration emails, reviews conversation context, identifies missing information, and drafts response emails—all while the user can multitask and mute the microphone between instructions. Second, the system can retrieve context from previous tasks and conversations, allowing users to resume work from days prior without manual searching. Third, voice mode coordinates multiple parallel agents simultaneously, demonstrated by creating three iPhone apps (Noto notes app, to-do list app, and link-saving app) in Swift UI with functional HTML prototypes—all initiated and managed through voice commands without writing code. Fourth, the system supports remote control via mobile phone through device linking and QR codes, allowing users to monitor computer tasks, create new jobs, and check progress from their phone using voice. Fifth, the transcript demonstrates scheduled automation where a daily task runs at 8 AM to research AI developments, identify content opportunities, and propose video ideas with titles, thumbnails, hooks, and sources—executing automatically without user intervention. The host emphasizes this represents a shift from voice-based question-answering to voice-directed task execution and agent coordination. A sponsored segment covers AllPass, a multi-AI platform consolidating ChatGPT, Claude, Gemini, and Grok access.
Key Insights
- Voice mode in Codex functions as real-time agent control rather than dictation—users can interrupt, mute, and change instructions on-the-fly while the AI continues executing tasks in the background
- The AI can review entire conversation history to understand context, identify missing information, and prepare contextually appropriate responses—detecting that a collaboration brief lacked specific deliverables, dates, and payment terms
- Multiple independent AI agents can be coordinated in parallel through voice commands, with each agent executing separate complex tasks simultaneously—three distinct iPhone app projects with different functionality built concurrently
- Remote control via mobile phone enables task monitoring and new job creation from anywhere by scanning a QR code to link devices, allowing users to manage computer-based work without physical proximity
- Scheduled automated tasks can run daily without user intervention—a content opportunity radar executing every morning at 8 AM to filter AI news, rank relevance to a YouTube channel, and propose video ideas with specific metadata
Topics
Transcript
[0:00] CH GPT has just received an update that on paper may seem quite small. You can now use voice mode directly within [music] Codex, but when you understand what this allows you to do, the possibilities are absolutely insane, because you no longer have to sit in front of the computer, type a prompt and wait for it to finish. Now you can talk to him while he works, interrupt him, change instructions on the fly, put multiple agents to work at the same time, and even continue controlling him from your [0:30] phone. And this means you can manage emails, research any topic, create complete applications, or have tasks run automatically using virtually only your voice. So in…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Migue Baena IA
‼️ Cambia entre Claude, ChatGPT y Gemini sin empezar de cero
A browser extension enables seamless switching between Claude, ChatGPT, and Gemini by saving conversation context and creating smart summaries. When one AI reaches its limit, users can load the summary into another model and continue without losing information or having to restart.
1.400 APIs gratis para tus proyectos
A GitHub repository provides access to over 100 free APIs organized into 50+ categories, including finance, news, sports, AI, and more. These pre-organized APIs enable developers to quickly build applications without creating infrastructure from scratch.
El prompt secreto de Anthropic 🤫🔥
A video claims that Anthropic has released Claude's full system prompt (120,000+ characters), which can allegedly be repurposed in cheaper or open-source models to replicate Claude's advanced reasoning capabilities and task-solving strategies.
NotebookLM en 2026, lo que realmente merece la pena
This video explores NotebookLM 2.0's powerful features for 2026, demonstrating how to use curated sources to generate reports, presentations, Excel files, and vertical videos. The tool works best as a structured context-based system rather than a general chatbot, transforming sources into actionable insights and multiple formats while requiring critical review of outputs.
🚨 6 skills de Claude que necesitas probar
The speaker identifies six essential Claude skills developed after testing over 100 options, focusing on workflow automation, planning, task management, code review, context preservation, and cross-session memory. These skills significantly improve project development speed, reduce errors, and eliminate repetitive work.