dsh-speak

Copy the command, or hand the whole task to your harness agent.

From the README

A cleaned excerpt from the project's own documentation.

dsh-speak 🔊 — Voice announcements for AI coding harnesses English · 中文 Let your agent tell you when a long task is done — no more staring at the screen. dsh-speak reads the final assistant reply aloud through system speech synthesis, using whatever voice the operating system is set to — on Windows the default SAPI voice (natural packs on Windows 11, or [NaturalVoiceSAPIAdapter] on Windows 10); on macOS the system reading voice ( say , Siri voices included). It was built for DeepSeek Harness and is structured so any harness can plug in. Features - Automatic : DSH web plugin watches the session event stream and announces the final reply (skips reasoning/tool-call narration, merges multi-step messages). - Gets your attention : announces approval requests (hears "需要你的审批" when the agent is waiting on you) and questions the agent asks via ask user question . - Final-reply replay (1.7.0):…

Project details

Repository

Alan2Z/dsh-speak

by

Alan2Z

License

MIT

stars

19

Forks

2

Updated

Oct 27, 2026

Created

Aug 14, 2026

Language

JavaScript

Indexed from

topic