← Back to list

dsh-voice-chat

DeepSeek Harness Other Low risk

Doubao-style voice chat for DSH: press-and-hold mic in the composer converts speech to text and auto-sends, and AI replies are read aloud. Optional LLM condensing (long replies summarized into short spoken lines, following the current conversation model), TTS-friendly text cleaning, selectable Edge TTS voices, adjustable silence auto-stop, and settings embedded in DSH settings dialog.

豆包式语音对话插件:聊天框麦克风按钮(按住说话)语音转文字并自动发送,AI 回复自动朗读。可选 LLM 转述精简(长回复压缩成口语再播,跟随当前对话模型)、朗读前清洗 markdown/emoji/特殊符号、Edge TTS 多种音色、静音自动结束时长可调,设置嵌入 DSH 自带设置弹窗(voice chat 类目)。

How to install

DeepSeek Harness dsh plugin add dsh-voice-chat

About

dsh-voice-chat 豆包式语音对话插件(DeepSeek Harness Web GUI):点一下 🎤 说话,AI 回复自动用语音"汇报"给你。 📖 完整使用手册见 MANUAL.md(安装/操作/配置/FAQ/原理)。 功能 **语音输入**:点 🎤 开始聆听("叮"提示音)→ 说话 → 停顿 2.5s 自动结束("咚")→ 转写并发送; **语音输出**:AI 回复经 edge-tts 合成朗读,语速 +10%;设置里可开「**转述朗读**」(默认关闭)——开启后较长回复会先由 LLM 以"助手本人"口吻**收敛转述**(≤原文长度、不发散、去代码表格)再播报,**转述用模型自动跟随当前对话在用的 LLM**(不再硬编码默认,避免默认模型被关/密钥错时转述失败); **单信道播报**:新回复抢占旧播报、按快捷键/点按钮立即打断,同一时刻只有一种声音; **防重播**:按会话记住已播报的回复,重进会话不重复朗读; **静音开关** 🔊:正在播报(按钮高亮)时点它**立刻静音**——马上停掉当前声音、清空全部待播队列;静音状态下再点一下恢复自动朗读; **设置入口**:设置项收进 **DSH 自带设置弹窗**(左下角齿轮 → 左侧「voice chat」类目):ASR 接口(Base URL / 模型 / API Key)、**识别后是否自动发送**、**长回复转…

Recommendation signals

49 Tool quality · Based on stars, downloads, maintenance, security and docs
User interest · Adjusted by in-site views, install copies and download clicks
49 Overall
0views
0unique visitors
0install copies
0download clicks
0outbound clicks

Meta

License
MIT
Language
JavaScript
GitHub stars
0
mo. downloads
Last push
2026-08-23
Created
2026-08-23

Links

Basic safety check

Findings
None
Sources
curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics
dsh-plugin, dsh-plugin-market, dsh-plugins

Related plugins

DeepSeek Harness New
Score64

dsh-voice-input-plugin

Zhangbo-cn/dsh-voice-input-plugin

Composer mic for the Web UI: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.

☆ 6 ↓ 456 Other
DeepSeek Harness
Score61

dsh-dingo

february2015/dsh-dingo

Sound reminders with one-click jump for concurrent sessions: the current session gets crisp dang/dang-dang tones, other sessions a soft ding/ding-ding plus a top-right card that jumps straight to the replying conversation.

☆ 1 ↓ 3.2K Other
DeepSeek Harness
Score60

dsh-perlica-ding

117BS/dsh-perlica-ding

Perlica (Arknights: Endfield) themed tiered sound notifications: plan-ready, task-done, needs-your-input, and error tones; silent for plain chat, system-level playback (works in background), cross-platform (Windows/macOS/Linux), custom TTS sounds.

☆ 5 ↓ 210 Other
DeepSeek Harness
Score59

dsh-plugin-notify-sound

ldchaowin/dsh-plugin-notify-sound

Per-workspace completion ringtones plus attention sounds for approval, question, plan-review, goal-blocked, and task-failure events, with built-in synth, voice (TTS), and custom audio.

☆ 5 ↓ 155 Other