Which AI tools do people use to control Claude Code and Codex by voice?

Across the 15 sourced use cases in this guide, the most used tools are Claude Code, OpenAI Codex, Grok Bot, Cursor, Wispr Flow.

How much does it cost to get started?

0 of the 15 use cases can start on a free plan. The most common paid starting price is $17/mo (11 use cases). Prices come from each tool's official pricing page.

How long does setup take?

2 of the 15 use cases list a setup time of an hour or less. Each card shows the setup time the builder reported.

Are these real examples?

Yes. Every use case links to its public source (an X post, a Hacker News thread or a GitHub repo) with the author and date, so you can check it yourself.

How to control Claude Code and Codex by voice

Short answer: You can drive Claude Code, Codex or Cursor by voice in two ways. The simple one is a dictation app such as Wispr Flow or a local Whisper-based tool that types what you say into the agent's prompt. The hands-free one is a purpose-built tool that sends speech straight to the agent and speaks short replies back: walkie-talkie remotes, AirPods controls, point-and-talk apps that pass what is on screen through MCP, or a Grok Bot that relays your voice to Claude Code. Local Whisper models keep audio on your computer and cost nothing per transcription. Use voice to describe what you want, and still read diffs on screen before you approve changes.

Voice setups for coding agents that builders use every day, from simple dictation to hands-free remotes that read the agent's replies back to you. 15 matching use cases below, each with a public source.

Looking for something else? Search all 1176 use cases or .

Get started in 3 steps

Try plain dictation into the agent's prompt first; it needs no new setup and shows whether talking actually speeds you up.
Prefer local speech-to-text (Whisper on your own machine) for private codebases, and remember a radio or speaker can be overheard.
Keep approvals on screen: voice is great for describing a task, but read the plan and the diff before letting the agent run commands.

Dev & opsX · @harshitagu72595

Control your coding agent with a walkie-talkie

walkai-talkai lets you talk to Cursor, Claude Code or Antigravity hands-free through a walkie-talkie and hear the agent's answers back over the radio, with local Whisper speech-to-text so audio stays on your Mac.

$17/mo1 hourIntermediate

Claude Code Cursor Antigravity

Automation & businessX · @KimNoel

Drive Claude Code by voice from Grok Bot

He starts Claude Code inside tmux and has Grok Bot's voice mode send it prompts through tmux, so he can talk to his coding agent and still watch the session.

$30/mo1 hourIntermediate

Grok Bot Claude Code tmux

Dev & opsX · @every

Build a local voice-to-text app with Claude Code

Matt Hartman used Claude Code to research local speech-to-text models on Hugging Face and build Ghost Pepper, an open-source dictation app that runs on your own computer so you do not pay per transcription.

$17/moDaysIntermediate

Claude Code Hugging Face

Dev & opsX · @doappwithai

Point at your screen and talk to your coding agent

Point and Yap by @maurermarc lets you tap Control twice, point at something on screen and talk; Claude Code, Codex or Cursor receives it through MCP, with on-device speech-to-text. Claude co-wrote 25 of its 30 recent commits.

$17/mo10 minBeginner

Claude Code OpenAI Codex Cursor

Personal & lifeX · @parthsuba77

Remove the ads from your smart TV home screen with Claude Code on your Mac

His TV showed an ad before he could even open Netflix, so he let Claude Code talk to it from his Mac. One evening later the ads and sponsored rows were gone, and every change can be reversed. He published a step-by-step guide plus the mistakes that cost him an hour.

$17/moAn eveningBeginner

Claude CodeSmart TV

Dev & opsX · @Sebasti54919704

Build your own code editor and talk to it with a full-duplex voice layer

He had Claude Code build a code editor shaped around how he works, and talks to his agents through Full-Duplex Code, an open-source voice layer for Claude Code and Codex.

$17/mo100 minIntermediate

Claude Code OpenAI Codex

Automation & businessX · @theaaron

Run daily Cursor cloud agents for meeting notes, email triage and morning briefings

The author runs scheduled Cursor cloud agents every day: one scrapes Wispr, Zoom and Gemini meeting transcripts into Obsidian, one triages Gmail, one updates a CRM with new leads, and one builds a morning briefing that Grok Bot prints out.

$30/mo1-2 hoursIntermediate

Cursor Wispr Flow Zoom

Creators & videoX · @PaulVictor50128

Get word-for-word transcripts for YouTube videos with no subtitles

He built a tool with Claude Code: paste a YouTube link and get a timestamped transcript as a .md file, with speech-to-text by Whisper running on Groq.

$17/mo1 dayBeginner

Claude Code Whisper Groq

Vibe coding & appsX · @patebry

Dictate to your coding agent

Use Wispr Flow to dictate tasks to Claude Code, which fans the work out to subagents running in the background.

$17/mo1-2 hoursIntermediate

Wispr Flow Claude Code

Dev & opsX · @danielfoch

Run your coding agents from your phone by voice

Use OpenClaw as a delegator for CLI coding agents so you can drive everything from voice notes on your phone.

$30/mo1-2 hoursIntermediate

OpenClaw Claude OpenAI Codex

Automation & businessX · @ericosiu

Hand repeatable business routines to an agent

A founder running $20M+ businesses rates Grok Bot top tier because it reliably runs repeatable routines.

$30/mo1-2 hoursIntermediate

Grok Bot OpenAI Codex Hermes Agent

Marketing & growthHacker News · jomon003

Ski: Voice Coding for Claude Code, Codex and More – On-Device – Free

Built Ski, voice Coding for Claude Code, Codex and More – On-Device – Free.

$17/mo1-2 hoursIntermediate

Claude Code OpenAI Codex

Dev & opsX · @doappwithai

Talk to Claude Code from across the room with AirPods

Earshot by @emadev01 has Claude speak a short line after each reply; you click an AirPods stem to dictate and nod to send. It was built with Claude Code and is open source.

$17/mo10 minBeginner

Claude Code

Vibe coding & appsX · @JulianGoldieSEO

Build apps by speaking one sentence

Set up voice input so a single spoken sentence like create a to-do list app has Claude Code write a working app live.

$17/mo1 dayIntermediate

Claude Code

Personal & lifeX · @PierreLore92322

Vibe-code a Mac voice app that types or runs agent actions

Vibe-coded a Mac dictation app with Claude Code: one mode types what you say, another runs agent actions across files, shell, AppleScript and any MCP server.

$17/mo1-2 daysIntermediate

Claude Code

Common questions

How do you control Claude Code and Codex by voice?: You can drive Claude Code, Codex or Cursor by voice in two ways. The simple one is a dictation app such as Wispr Flow or a local Whisper-based tool that types what you say into the agent's prompt. The hands-free one is a purpose-built tool that sends speech straight to the agent and speaks short replies back: walkie-talkie remotes, AirPods controls, point-and-talk apps that pass what is on screen through MCP, or a Grok Bot that relays your voice to Claude Code. Local Whisper models keep audio on your computer and cost nothing per transcription. Use voice to describe what you want, and still read diffs on screen before you approve changes.
Which AI tools do people use to control Claude Code and Codex by voice?: Across the 15 sourced use cases in this guide, the most used tools are Claude Code, OpenAI Codex, Grok Bot, Cursor, Wispr Flow.
How much does it cost to get started?: 0 of the 15 use cases can start on a free plan. The most common paid starting price is $17/mo (11 use cases). Prices come from each tool's official pricing page.
How long does setup take?: 2 of the 15 use cases list a setup time of an hour or less. Each card shows the setup time the builder reported.
Are these real examples?: Yes. Every use case links to its public source (an X post, a Hacker News thread or a GitHub repo) with the author and date, so you can check it yourself.

More how-to guides