dsh-voice-suite
chentao4183/dsh-voice-suite
DSH 语音套件:免费 edge-tts 页内播报 + 语音转文字输入(百炼 paraformer-realtime-v2)+ Alt+Q 快捷键 + 自动发送 | Speech suite: free edge-tts announce + speech-to-text input (Bailian paraformer) + hotkey
0
stars
0
forks
NOASSERTION
License
2026-08-16
Created
2026-08-16
Last push
README
dsh-voice-suite · 语音套件
English | 中文
DSH(DeepSeek Harness)语音交互套件:免费微软神经音色的页内播报 + 快捷键语音输入,基于 dsh-speech-plugin(MIT)定制增强,edge-tts 协议实现收编自 dsh-voice(MIT)。
功能
- 🔊 每条回复可播报:消息操作条的喇叭按钮,页内直接朗读(自动剥离 markdown/表情,跳过代码块)
- 📣 自动播报开关:会话头部开关,开启后新回复自动朗读(浏览器本地记忆)
- 🆕 edgetts 免费引擎:页内播报走微软 edge-tts 协议——22+ 神经音色、可调语速音调、 零 API key、零成本、无限量;也可切换系统音色 / 阿里百炼 / 火山豆包
- 🎤 语音转文字(语音输入):麦克风 → 阿里百炼
paraformer-realtime-v2实时识别 → 文字进输入框, 实时出字、句末自动加标点;也可切换火山豆包。链路:麦克风 → 浏览器采集 PCM → 插件 WebSocket → 百炼实时识别 → 文字落入输入框 - ⌨️ 键盘快捷键(默认
Alt+Q):轻按 = 开始/结束录音;长按 ≥300ms = 按住说话松开结束 - 📤 录音结束自动发送(可关)
- 🛑 录音自动打断播报:开始说话即停朗读,防回声串台
安装
npx -y @deepseek-ai/dsh plugin --profile web add <你的GitHub用户名>/dsh-voice-suite
# 或本地目录
npx -y @deepseek-ai/dsh plugin --profile web add /path/to/dsh-voice-suite
语音输入需要 ASR 密钥(页内播报不需要,edgetts 完全免费):
# ~/.dsh/.env
SPEECH_DASHSCOPE_API_KEY=sk-... # 阿里百炼(推荐,每月免费 10 小时)
# 或 SPEECH_VOLCENGINE_API_KEY=...
语音识别引擎说明(ASR)
语音输入(麦克风 → 文字)默认使用阿里云百炼的实时语音识别大模型:
| 项目 | 说明 |
|---|---|
| 默认模型 | paraformer-realtime-v2(百炼实时识别,中文标点自动加) |
| 免费额度 | 每月 36,000 秒(10 小时),每月 1 日自动发放 |
| 超出计费 | 0.00024 元/秒 ≈ 0.86 元/小时,按实际秒数 |
| 申请入口 | 百炼控制台 → API-KEY(sk- 开头) |
也可切换火山豆包(asrEngine: volcengine,需控制台 API Key)。
换识别模型:配置项 dashscopeAsrModel(默认 paraformer-realtime-v2)。
注意:百炼账户欠费会同时禁用语音输入(Arrearage 策略),语音输入突然失效先查控制台余额。
配置(profile 的 cordis.patch.yml)
- id: ui-speech
name: dsh-voice-suite
config:
engine: edgetts # auto | system | dashscope | volcengine | edgetts
edgeVoice: zh-CN-XiaoxiaoNeural # 微软神经音色,400+ id 可选
edgeRate: '+20%' # 语速 -50% ~ +100%
edgePitch: '+0Hz' # 音调
asrEngine: dashscope # auto | off | dashscope | volcengine
浏览器端个人化(F12 控制台设置,刷新生效):
localStorage.setItem('dsh.speech.micHotkey', 'Ctrl+M') // 换快捷键
localStorage.setItem('dsh.speech.autoSend', '0') // 关自动发送
常用音色
| 音色 id | 声音 |
|---|---|
zh-CN-XiaoxiaoNeural |
晓晓 · 温柔女声 |
zh-CN-YunjianNeural |
云健 · 浑厚男声 |
zh-CN-YunyangNeural |
云扬 · 新闻男声 |
zh-CN-liaoning-XiaobeiNeural |
晓北 · 东北话 |
zh-CN-shaanxi-XiaoniNeural |
晓妮 · 陕西话 |
zh-HK-HiuMaanNeural |
曉曼 · 粤语 |
en-US-AriaNeural |
Aria · 美式英语女声 |
完整清单见微软 Speech 服务语音目录,合法 id 均可填。
许可
MIT。衍生自两个 MIT 上游项目(见 LICENSE)。
English
dsh-voice-suite
A speech interaction suite for DSH (DeepSeek Harness): free Microsoft-neural-voice in-page announce + hotkey voice input, customized from dsh-speech-plugin (MIT), with the edge-tts protocol implementation adopted from dsh-voice (MIT).
Features
- 🔊 Speak any reply in-page via the per-message horn button
- 📣 Session-level auto-announce toggle (persisted per browser)
- 🆕 edgetts engine: page announce over the Microsoft edge-tts protocol — 22+ neural voices, adjustable rate/pitch, no API key, no cost, unlimited; system voices / Aliyun DashScope / Volcengine remain selectable
- 🎤 Speech-to-text voice input: mic → Aliyun Bailian
paraformer-realtime-v2realtime ASR → text lands in the composer with live partials and auto punctuation; Volcengine also selectable. Pipeline:mic → browser PCM capture → plugin WebSocket → Bailian realtime ASR → composer - ⌨️ Hotkey (default
Alt+Q): tap = toggle; hold ≥300ms = push-to-talk - 📤 Auto-send the transcript when recording ends (disable via localStorage)
- 🛑 Recording interrupts any in-flight announce (echo guard)
Install
npx -y @deepseek-ai/dsh plugin --profile web add <your-github-user>/dsh-voice-suite
Voice input needs an ASR key (announce does not — edgetts is free):
# ~/.dsh/.env
SPEECH_DASHSCOPE_API_KEY=sk-...
Configuration
See the YAML block above; row id is ui-speech, engine values
auto | system | dashscope | volcengine | edgetts.
Voice input defaults to Aliyun Bailian (DashScope) realtime ASR — model
paraformer-realtime-v2, free tier 36,000 seconds (10 h) per month, then
¥0.00024/s; get an sk- key at the Bailian console.
Full details in the Chinese section above.
License
MIT. Derives from two MIT upstreams (see LICENSE).
More in Voice & Speech
dsh-voice-ai-girlfriend
by beiyege-01
语音 AI 女友(Voice AI girlfriend for DeepSeek Harness):Whisper 语音输入 + Qwen3-TTS 声音克隆 + 句子级流式朗读 + 数字人动画窗。插话/排队双模式,说话即打断。
dsh-voice-input
by forrestahha
Voice-to-text input plugin for the DeepSeek Harness Web UI
dsh-voice-mic
by zachary7456
DeepSeek Harness (dsh) 语音输入插件:麦克风按钮/快捷键录音,实时转写回填输入框。三种识别引擎:浏览器 Web Speech、本地 SenseVoice/Paraformer 离线后端(一键部署)、OpenAI 兼容云端 ASR API。
deepseek-harness-voice-context
by charlesliuzc
DeepSeek Harness with Voice Context speech-to-text integration
