Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 10 additions & 6 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,20 +1,24 @@
# GPT-VoiceCoding

**A macOS menu-bar app for voice control of Claude Code and Codex**
**A macOS menu-bar app that speaks up when a Claude Code or Codex session stops and sends your answer, spoken or typed in Telegram, back to that session**

**English** · [简体中文](./README.zh-CN.md)

![macOS](https://img.shields.io/badge/macOS-only-111111)
![Apple Silicon](https://img.shields.io/badge/Apple%20Silicon-required-111111)
![Licence](https://img.shields.io/badge/licence-MIT-111111)

I don't want to sit at the screen while my coding agents work. I'd rather get up and move around.
I usually have several Claude Code and Codex sessions running, and when one stops I want to find
out which one and what it stopped on, then keep it going in plain language: by talking it through
with GPT-Live, or by replying on Telegram.

https://github.com/user-attachments/assets/a0ea108c-8c5b-45a1-b966-877a05650c65

One voice call covers every Claude Code and Codex session on your Mac. When a session stops, it
calls you: you hear which session stopped and what it stopped on, and your spoken answer goes back
into that session. Away from the desk, you answer on Telegram. The call uses OpenAI's GPT-Live
voice model through `codex app-server`'s realtime route, so it runs on the ChatGPT account you
signed `codex` into and you don't need an OpenAI API key.
One voice call covers every Claude Code and Codex session on your Mac, and each answer goes back
to the session it was meant for. The call uses OpenAI's GPT-Live voice model through
`codex app-server`'s realtime route, so it runs on the ChatGPT account you signed `codex` into
and you don't need an OpenAI API key.

## How it works

Expand Down
6 changes: 4 additions & 2 deletions README.zh-CN.md
Original file line number Diff line number Diff line change
@@ -1,16 +1,18 @@
# GPT-VoiceCoding

**用语音操控 Claude Code 和 Codex 的 macOS 菜单栏应用**
**一个 macOS 菜单栏应用:Claude Code 或 Codex 的会话停下时,它会出声告诉你,再把你的回答(语音或 Telegram 消息)送回那个会话**

[English](./README.md) · **简体中文**

![macOS](https://img.shields.io/badge/macOS-only-111111)
![Apple Silicon](https://img.shields.io/badge/Apple%20Silicon-required-111111)
![Licence](https://img.shields.io/badge/licence-MIT-111111)

我不想一直守在屏幕前看编程 agent 干活,更想起来走动走动。我手上通常同时跑着好几个 Claude Code 和 Codex 会话,其中一个停下来时,我想知道是哪个、停在哪儿,然后用平常说话的方式让它接着做:跟 GPT-Live 聊,或者在 Telegram 上回一句。

https://github.com/user-attachments/assets/a0ea108c-8c5b-45a1-b966-877a05650c65

一通语音电话,照看你 Mac 上所有的 Claude Code 和 Codex 会话。某个会话停下来,它就给你打电话:你会听到是哪个会话停了、停在什么地方,你开口回答,这句话会送回那个会话。不在电脑前时,在 Telegram 上回复也行。通话用的是 OpenAI 的 GPT-Live 语音模型,走 `codex app-server` 的实时通道,所以用的就是你登录 `codex` 的 ChatGPT 账号,不需要 OpenAI API key。
一通语音电话,照看你 Mac 上所有的 Claude Code 和 Codex 会话,每个回答都会送回它该去的那个会话。通话用的是 OpenAI 的 GPT-Live 语音模型,走 `codex app-server` 的实时通道,所以用的就是你登录 `codex` 的 ChatGPT 账号,不需要 OpenAI API key。

## 工作原理

Expand Down
Loading