STARDUSTLC666/dsh-voice

DeepSeek Harness 语音双件套插件：voice_tts（edge-tts 协议免费微软神经语音合成，Sec-MS-GEC 本地 DRM 生成）/ voice_stt（OpenAI 兼容 ASR）/ voice_list。· TTS + STT for DeepSeek Harness agents.

Bundle verified Unknown TypeScript Unknown
Bundle verified

Listed

2

Voice

Bundle verified

★ 2 View on GitHub
VersionUnknown
LanguageTypeScript
LicenseUnknown
View on GitHub

Preview

Preview 1 of 2: STARDUSTLC666/dsh-voice
Preview 2 of 2: STARDUSTLC666/dsh-voice

What it does

Voice pair: free edge-tts neural speech synthesis + OpenAI-compatible ASR transcription.

Best for

  • Agents that need to synthesize MP3 speech from text with selectable Microsoft neural voices.
  • Teams transcribing audio through Groq, OpenAI, or another OpenAI-compatible ASR endpoint.
  • Chinese and English voice workflows that benefit from configurable voice, rate, pitch, language, and transcription prompts.

Not ideal for

  • Offline speech workflows, because synthesis and transcription rely on remote services.
  • Speech-to-text use without credentials for a configured ASR provider.
  • Inputs exceeding the documented limits of 5,000 text characters for TTS or 25 MB per audio file for STT.

README

English

dsh-voice

你的 agent 会说话了：edge-tts 微软神经语音免费无限量 + Whisper 转写。

npm version npm downloads license stars

Awesome DSH Plugin

DSH（DeepSeek Harness）语音双件套插件：让 agent 会说话、能听懂。

  • voice_tts：文字转语音，走 edge-tts 协议（微软 Edge 朗读服务，免费无限量，22+ 常用音色）
  • voice_stt：语音转文字，走 OpenAI 兼容 ASR 接口（Groq / OpenAI / 自定义端点）
  • voice_list：音色清单

安装

dsh plugin --profile web add dsh-voice

配置

voice_tts 零配置可用；voice_stt 需要 ASR 密钥：

- id: voice
  name: 'dsh-voice'
  config:
    asrEngine: groq                       # groq | openai | custom
    asrModel: whisper-large-v3-turbo      # groq 的 whisper 模型
    # asrApiKey: gsk_...                  # 推荐改用环境变量 DSH_VOICE_ASR_KEY
    ttsVoice: zh-CN-XiaoxiaoNeural        # 默认音色
    # proxyUrl: http://127.0.0.1:7890     # ASR 接口需要特殊代理时启用

工具一览

工具 作用 关键参数
voice_tts 文字合成 MP3（免费） text 必填；voice/rate/pitch/output 可选
voice_stt 音频转文字 audio 必填；engine/model/language/prompt/output 可选
voice_list 常用音色清单 无
示例
voice_tts { text: 今天的 AI 早报来了 }                    # 晓晓女声，输出 voice_output.mp3
voice_tts { text: hello, voice: en-US-AriaNeural }        # 英文女声
voice_stt { audio: E:\audio\meeting.mp3, language: zh } # 转写会议录音
voice_list {}

硬核细节

  • edge-tts 协议直连：Sec-MS-GEC 令牌按官方 DRM 算法本地生成（SHA256(Windows 文件时间 + TrustedClientToken)，5 分钟窗口），WS 传输用 ws 库 + permessage-deflate 压缩 + 可选 HTTP CONNECT 代理隧道
  • 零 API 成本：TTS 完全免费；STT 只花你选的 ASR 接口的钱
  • 文本 ≤5000 字符、音频 ≤25MB 前置校验；输出同名自动加序号
  • 协议对齐开源 edge-tts 当前版本（7.x），不依赖过时的令牌端点

开发

pnpm install
pnpm test       # 构建 + 31 个测试（含真实合成集成测试）

License

MIT

Frequently Asked QuestionsFAQ

Use the verified command dsh plugin --profile default add github:STARDUSTLC666/dsh-voice in a DSH-enabled shell. The command resolves the public package metadata and keeps the plugin attached to the catalog identity shown on this page.

zhu1090093659/dsh-web-ui#packages/dsh-web-ui-all★ 4,306

Plugin and skin collection for the DSH Web UI: task board, Git graph, right-side panel, remote mobile UI, pet, live token stats, and a skin center.

Apache-2.0
omdsh-dev/DSH-better-sidebar★ 2,046

Full sidebar workbench with file rendering and editing, terminal, Git, and subagents; third-party plugins can register new tabs.

MIT
ccch1mneyyy/dsh-TUI★ 1,892

Claude Code-style full-screen terminal UI: pixel-whale header, live status line, and streaming thought expansion.

MIT
omdsh-dev/dsh-at-file★ 354

Codex-style `@file` mentions: search workspace files in the composer and attach their contents to prompts.

MIT