Field guide / primary domain
11
sources in this field
Updated July 28, 2026
Current thesis
The shortest path to orientation.
Voice is shifting from generation-centric to a local-first, agent-integrated model with commoditized synthesis. Voicebox (Qwen3-TTS) achieves near-perfect voice cloning locally without cloud dependency, threatening paid APIs and signaling synthesis commoditization. Real-time transcription (GPT Realtime Whisper at $0.017/minute) streams queryable transcripts; local alternatives like Nemotron are cost-effective options. Speech-to-text tools like Monologue drive coding agents more efficiently than typing. Fluid mid-conversation modality switching (text, voice, video, live calling) within one agent session is now baseline rather than separate product surface. Operationally, treat Voice as a chief of staff answering questions (not a direct worker), designating one device as HQ with others as remote nodes. Maintain a compass doc per project listing short/long-term goals so Voice recommends coherent next steps. This 3-step cycle ('where do we stand' → 'what's next' → 'spin up a thread') reportedly increased productivity 10x over two days by lowering cognitive load and delegating brainstorming to the AI.
Evidence board
Claims worth carrying forward01Workflow: open ChatGPT Voice, ask for status + recommended next step on all current projects, approve recommendations, brain-dump on one project, iterate until an idea forms, then say 'start a thread on that' and 'what's next' — repeat across projects.
02Core principle: treat Voice as a chief of staff you ask questions of (more questions than commands), not a worker you command directly — Voice itself doesn't do the work, it hands off good ideas to dedicated agents/threads on your main machine.
03Setup tips: keep a 'compass' doc per project listing short/long-term goals so Voice can recommend next steps from it; designate one device as HQ and use others as remote nodes into it (e.g., ChatGPT iOS remoting into a Mac Studio during walks).
04Claimed productivity effect: this 3-step cycle ('where do we stand' → 'what's next' → 'spin up a thread') made the author 10x more productive over 2 days versus prior workflows, attributed to lower cognitive/energy load from delegating brainstorming to the AI.
05Practical resource note: this voice-orchestration strategy consumes credits quickly, so use medium-thinking models for spun-up threads and reserve lighter/faster models (referred to as 'luna and terra') when appropriate; also recommend building a 'morning work' skill that scripts how the agent audits projects and proposes next steps.
06Codex Meeting Recorder skill uses GPT Realtime Whisper to transcribe meetings live, display transcripts in the preview pane, and answer questions about the transcript mid-meeting — full transcript plus formatted summary generated on completion.
07GPT Realtime Whisper endpoint costs $0.017/min (~$0.51 for a 30-min meeting), meaningfully more expensive than post-meeting batch transcription. This is the core cost tradeoff for choosing real-time vs. deferred transcription.
08Nemotron Speech Streaming is cited as a candidate local real-time transcription alternative to GPT Realtime Whisper, potentially eliminating per-minute cloud costs for Codex meeting transcription.
Adjacent fields
Latest evidence
Alex Finn
Alex Finn describes ChatGPT Voice as a productivity-transforming AGI moment, using it as a conversational orchestrator that delegates work to agents/threads rather than doing tasks itself, with a specific daily workflow and setup tips.
Simon Smith
A Codex skill enables real-time meeting transcription via GPT Realtime Whisper, with live Q&A on the transcript during the meeting. Cost is $0.017/min (~$0.51 per 30-min meeting). A local alternative using Nemotron Speech Streaming is under consideration.
Samantha Trimble
A one-time setup prompt for Codex (or similar coding agents) that ingests a user's own sent emails and Slack messages read-only, extracts writing-style patterns into a reusable 'my-voice' skill, and uses a feedback loop of comparing drafts to actually-sent messages to keep the skill updated—while enforcing strict guardrails that the agent may only draft, never send.
Antaripa Saha
> Do automated evals actually work? > > I and @HamelHusain spent last few weeks testing the auto-evals efficacy of different evals platforms.
Simon Smith
> You can now transcribe meetings in real time using Codex and ask Codex questions about meetings as they're happening! > > I updated my new Codex Meeting Recorder skill to use GPT Realtime Whisper. Tell Codex to use the skill, and it will start transcription and show it in the preview pane. You ca
Soumitra Shukla
> For working on frontend (e.g., slides) with GPT 5.5 + Codex, ask it to generate prototypes first of what you want using the imagegen model. And then ask the 5.5 to implement. Works like a charm > **Quoted @soumitrashukla9:** > Everyone gives lists and long essays on how to use Claude Code or Codex
Peter Yang
> A great personal agent should: > > 1. Get work done across email, calendar, Google Workspace, or any API/MCP it's hooked up to
rLLM
> https://t.co/Dl67Q7wMgx - The rLLM project has released a new version, which includes updates to the [[claude]] architecture, design, and ecosystem - The new release introduces support for [[voice-tools]] and [[physical-ai]] integrations, enabling new use cases for the [[claude]] language model
klöss
> https://t.co/p2ldwjt7kj - Claude can assist with a variety of tasks, including [[b2b-growth]], [[brand-and-design]], and [[physical-ai]] — as demonstrated by the linked example of Claude interacting with the physical world through a camera feed - The tweet showcases Claude's ability to understand
Shiv
> Lots of companies are now building primitives for an economy where AI agents are the primary users instead of humans. > > They're betting on an economy of AI coworkers.