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
Cómo aprender por tu cuenta y volverte imparable con IA
This tutorial demonstrates how to use Gemini Notebook (formerly Notebook LM) to self-teach any skill by curating personal learning sources and converting them into multiple study formats. The four-step process involves selecting quality materials, studying them through different media, teaching the content to others, and integrating learning into daily routines.
Tienes que probar esto antes de crear tus videos con IA 🎬
A new AI video creation tool called 3D Builder within Topw Film Studio allows creators to pre-visualize and plan movie scenes by building interactive 3D environments, positioning characters and objects, controlling camera movements, and reviewing animations before final video generation.
No elijas entre Claude y Codex: úsalos juntos 🤝🏻
The video proposes using Claude and Codex together rather than choosing one over the other to maximize their respective strengths. Claude handles problem analysis and task delegation while Codex executes code generation, allowing users to work around individual API rate limits and leverage complementary capabilities.
Cómo usar Claude mejor que el 99% de la gente
A comprehensive guide to using Claude AI effectively, covering account setup with context import, model selection and reasoning levels, proper prompting techniques, projects and skills for organizing work, and advanced features like Cowork for delegated tasks and Code for building applications.
El archivo de GitHub que deberías de conocer 👀
Anthropic has published a detailed GitHub repository containing a 275,000+ character PRD with nearly 8,000 lines of instructions for one of their models, including specifications on what to do, avoid, and how to use tools. The key value lies not in copying the content but in studying its structure and learning how it organizes rules and defines tool usage for prompt engineering applications.