allmodels-io/dsh-speech

Name: allmodels-io/dsh-speech
Author: allmodels-io

Plugin插件 Native原生 ⭐ 3 MIT Vision & Media视觉与多媒体 Sessions & Context会话与上下文

Real-time voice input and spoken answer summaries for DeepSeek Harness.

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

dsh-speech is a DeepSeek Harness plugin that adds speech-to-text and text-to-speech capabilities. It lets you dictate prompts to a coding agent via microphone with live transcription, then play a spoken summary of the agent's final reply. Use it when you prefer voice interaction over typing. Note: it requires an AllModels account or API key, and needs DSH web profile 0.1.1-rc.2 with Node.js 22.19+ or 24+.

dsh-speech 是 DeepSeek Harness 语音插件，提供语音转文字与文字转语音能力。适用于通过麦克风向编码代理口述指令并实时看到转录结果，以及在代理完成后播放最终回复的语音摘要。注意：需绑定 AllModels 账户或 API Key，并要求 DSH web profile 0.1.1-rc.2 及 Node.js 22.19+ / 24+。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我了解并安装插件：【dsh-speech】【https://github.com/allmodels-io/dsh-speech】

Send this message to DSH in your current session. CLI install commands may not be accurate across systems — DSH will figure it out for you.把上面这条消息直接发给当前会话里的 DSH，让它帮你了解并安装。安装命令不一定准确，发给 DSH 更稳。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add @allmodels/dsh-speech

把 allmodels-io/dsh-speech 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

1.9 KB · 缓存于 2026-09-14 19:40:21 · 1.9 KB

Live speech transcription in DeepSeek Harness

@allmodels/dsh-speech

The speech plugin DeepSeek Harness deserves.

Talk to your coding agent, see your words appear in real time, and hear a concise spoken summary when the work is done. Powered by AllModels.io.

Demo

https://github.com/user-attachments/assets/a727afab-777d-487d-a145-175f5e570eca

Install

dsh plugin --profile web add @allmodels/dsh-speech

Restart DeepSeek Harness, then open Settings → Speech.

Connect AllModels

Enter your email address and AllModels will send you a sign-in code. New accounts get $1 free credit, which should last for plenty of hours of transcription and spoken summaries.

Already have an AllModels API key? You can use that instead.

Talk to your agent

Click the microphone next to Send and start talking. Your transcript appears as you speak, ready to edit or send.

Live transcription and microphone selection in DeepSeek Harness

Hear the summary

When the agent finishes, the plugin turns its final message into a short spoken summary. Enable autoplay to hear it immediately, or play it whenever you want.

Settings

Recognition

Speech recognition settings in DeepSeek Harness

Spoken summaries

Spoken summary and voice settings in DeepSeek Harness

Compatibility

DeepSeek Harness web profile 0.1.5-rc.2
Node.js ^22.19.0 || >=24.0.0
Local DeepSeek Harness web client

Contributing

Development, testing, release, and compatibility-monitoring notes are in CONTRIBUTING.md.

License

MIT

渲染基于仓库 allmodels-io/dsh-speech 的 README.md。在 GitHub 查看原文 →

CLI Install命令行安装 Copy Install复制安装命令