Skip to content
The Definitive Guide to Using Voice With AI
Midjourney/Every illustration.

The Definitive Guide to Using Voice With AI

A five-step voice workflow—and more than a dozen prompts—for turning raw speech into finished work

· 2 min read

Comments

TL;DR: Our new guide, “Build Faster With Voice,” shows you how to turn raw speech into finished work with AI agents. Join us on Friday, August 7, for Voice Mode Camp, a one-hour live session where the Every team will demo practical voice workflows for writing and agent orchestration, help you get started, and answer your questions.—Kate Lee

Was this newsletter forwarded to you? Sign up to get it in your inbox.


Most knowledge work still starts with an act of translation. You finish a customer call and turn it into a bug report. You think through a story idea on a walk, then wait until you’re back at your laptop to organize it. Before the real work can begin, you’ve already spent time cleaning up the context.

Paired with an AI agent, voice can remove that intermediate step. You can speak while the details are fresh, point the agent toward the relevant transcripts, code, documents, or messages, define the outcome you want, and review what it produces.

A useful way to start is with a five-step loop:

Capture → retrieve and ground → define the outcome → act → review and redirect

Today we’re publishing “Build Faster With Voice,” a practical guide to using that loop across writing, planning, software, communication, and ongoing memory systems.

The full guide is available to paid and All Access Every members. It includes:

  • More than a dozen workflows based on how people at Every use voice with agents
  • Copyable prompts for turning recordings into article outlines, project plans, bug patches, emails, meeting follow-ups, and more
  • Setup instructions for connecting your notes and transcripts to Codex or Claude
  • The context, safeguards, and review steps each workflow needs

If you’re reading Every for free, the five-step loop above is yours to try. To get the complete prompts, setup instructions, and workflow library, you’ll need to upgrade to a paid Every subscription.

Voice doesn’t eliminate the need for good sources or careful review. Agents still need access to the material that has the final say, and consequential actions should still require your approval. The advantage is that you no longer have to turn every messy thought into polished instructions before the work can start.


Naveen Naidu is the general manager of Monologue. You can follow him on X at @naveennaidu_m and on LinkedIn.

Laura Entis is a staff writer at Every. You can follow her on LinkedIn.

To read more essays like this, subscribe to Every, and follow us on X at @every and on LinkedIn.

Everyone’s a builder now. Every All Access gets you the full membership plus the Builder Pack—$9,000+ in credits for the tools we build with.

The Only Subscription
You Need to Stay at the
Edge of AI

The essential toolkit for those shaping the future

"This might be the best value you
can get from an AI subscription."

- Jay S.

Every ContentEvery Content
AI&I PodcastAI&I Podcast
MonologueMonologue
Every AgentEvery Agent

Join 100,000+ leaders, builders, and innovators

Community members

Already have an account? Sign in.

What is included in a subscription?

Daily insights from AI pioneers + early access to powerful AI tools

PencilFront-row access to the future of AI
CheckIn-depth reviews of new models on release day
CheckPlaybooks and guides for putting AI to work
CheckPrompts and use cases for builders

Related Essays

Comments

You need to login before you can comment. Don't have an account? Sign up!

We use analytics and advertising tools by default. You can update this anytime.