Voice transcription for IDE extension

What feature would you like to see?

Do you have a plan to add a mic button (push‑to‑talk) in the Codex panel so we can dictate prompts and follow-ups directly? If this is already on the roadmap, could you share an ETA?

Related: #418 (voice mode for CLI).

Are you interested in implementing this feature?

I wish I could 🙂.

I use superwhisper.. its perfect for dictation

This would be super helpful!

Would love this. I've jumped through hoops today trying to find a way to make this work, but at present, VScode only seems to allow dictation in a file, or with the other built-in chat.

Just use Superwhisper.

@anfedoro

@anfedoro not everyone is on a Mac! A solution for WSL would be very welcome.

This feature will really help to enhances the experience.

Up !!!

Can we have both dictation and a voice back for a proper conversation?

Claude Code just released /voice for input dictation

we need this back please for the CLI!

@etraut-openai

@etraut-openai Is there an estimated release date? I am using ChatGPT Pro on Windows to log into the Codex CLI and still cannot use voice input, but it is already available on macOS.

I think this macos foxuse it's wrong. You should support Linux better.

Claude Code IDE extension for VS Code seems to have this feature already as well and some users in openai's dev forum have been asking for it since Dec 2025

what's the holdup?

also need this because look like already have on codex app

I have created my own "Super Whisper" for Linux: https://github.com/phplego/mywhisper
Maybe someone will find it useful.

Anyway, it would be really useful and straightforward if the extension had its own voice input.

+1 for push-to-talk dictation in Codex, especially if the transcript lands in the prompt box for review before it is sent.

A few edge cases that matter a lot for non-English AI coding workflows:

mixed-language prompts are common: Chinese users often say things like “帮我 refactor 这个 React hook” rather than pure Chinese or pure English;
the user should be able to edit the transcript before Codex executes anything, because ASR mistakes can easily become wrong tool instructions;
language hints and glossary/hotword hints would help with filenames, APIs, framework names, and repo-specific terms;
voice transcripts should be treated as sensitive prompt material: avoid logging raw audio paths, raw transcripts, cleaned transcripts, or final user-confirmed prompts by default;
if local/on-device transcription is supported, fallback to cloud transcription should be explicit rather than silent.

For reference, I’m maintaining an open-source local-first Chinese / mixed Chinese-English voice typing project for macOS: https://github.com/botaruibo/MyVoiceTyping

Different product surface from Codex, but the AI coding prompt workflow is very similar: hold to speak → clean up the text → insert into the active input → user reviews before sending.

I'm on Windows so I tend to use the Windows Key + H for native voice to text, but tbh it's not great, doesn't automatically do punctuation, and keeps changing because to 'cause which I find very annoying. The only benefit is that it's built in and I didn't waste any time setting something up.

I don't understand why OpenAI haven't added this yet, they clearly have had good voice capability for a while. Now the Claude vscode plugin's voice is really very good as others have already pointed out above. This isn't a good look for codex in vscode...

Hi Codex team — dictation is useful, but the feature I want most is true real-time, two-way voice collaboration: I speak, Codex responds by voice, and I can interrupt or redirect it while a task is running, with both of us sharing the same screen context.

I started as a product operations professional with zero coding background. With Codex, I can now independently build full-stack tools and have shipped several real products.

I believe voice + screen + text, with visual confirmation for risky actions, would make Codex dramatically more accessible to product people, operators, and new builders.

I’d be very happy to share my workflow or participate in user research.

— Boyuan Liu

I strongly support adding native microphone/voice dictation directly to the Codex VS Code extension.

I use Codex for React Native and Expo development, and typing long debugging, architecture, and coding instructions repeatedly takes a lot of time. A microphone button inside the Codex chat box would make the workflow much faster and more natural.

Please make the voice input multilingual rather than English-only. Support for major languages around the world would make Codex much more accessible globally. In particular, please consider Bangla (Bengali), as this would be very valuable for Bangla-speaking developers.

I have used Claude Code as well, and voice interaction is one area where it can feel more convenient. Adding this feature to Codex could make Codex more competitive, improve the daily developer experience, and potentially attract and retain many more users.

I am already using Codex, and this feature would make a significant difference to my development workflow. I strongly hope the team considers it.

Voice-input safety / correction UX suggestion

Author: Almási Andor Aladár

If voice transcription is added to the IDE extension, I would strongly recommend treating transcription confidence as part of the interaction design rather than inserting text as if every token were exact.

A minimal safe flow:

insert the transcript as editable text before execution;
flag or preserve uncertainty around low-confidence names, paths, numbers, commands, and technical terms;
use sentence-level context to detect obviously implausible substitutions;
require confirmation when an uncertain transcription would materially change a tool action;
never let a questionable ASR token silently authorize a destructive operation.

A short userland intent rule is: interpret the full sentence and current task before treating an anomalous transcribed token as the user's actual instruction.

Navigation Menu

Repository navigation

Voice transcription for IDE extension #3000

What feature would you like to see?

Are you interested in implementing this feature?

19 remaining items

Voice-input safety / correction UX suggestion

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Voice transcription for IDE extension #3000

Description

What feature would you like to see?

Are you interested in implementing this feature?

Activity

anfedoro commented on Sep 1, 2025

whoschek commented on Sep 25, 2025

interconnectedMe commented on Nov 13, 2025

anfedoro commented on Nov 14, 2025

eschulma commented on Nov 15, 2025

Kuntalthakur01 commented on Nov 18, 2025

pforques commented on Dec 3, 2025

anathefish commented on Dec 9, 2025

19 remaining items

matheuscscp commented on Mar 12, 2026

RogelioRichmanAstronaut commented on Apr 1, 2026

doggy8088 commented on Apr 2, 2026

stalkerg commented on Apr 2, 2026

QuanDeFi commented on May 13, 2026

janeza2 commented on May 23, 2026

phplego commented on Jun 14, 2026

botaruibo commented on Jul 16, 2026

cosmicnet commented on Jul 19, 2026

784275918-debug commented on Jul 23, 2026

azadmandalmd-hub commented on Aug 22, 2026

hyperbetteri commented on Sep 1, 2026

Voice-input safety / correction UX suggestion

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions