Bundle
dsh-asr-voice
开口即成文 · Speak-to-prompt for DeepSeek Harness：云端 ASR 语音识别 + 提示词优化 + 填入草稿/自动发送，跨平台 macOS / Windows。
bitterSmilezzz
Browse
38 results
Bundle
xby-asr-1
通用语音识别，支持多国语言及小语种。
xby-skill
Bundle
dsh-listener
安全版本地语音输入插件 for DeepSeek Harness:输入框右侧麦克风按钮,录音后经同源宿主代理转写(本地 SenseVoice-Small INT8 ONNX,音频不出网)。后端仅绑定 127.0.0.1 + 随机 token,无 CORS,模型 sha256 校验。
Lanzgale
Bundle
dsh-voice-live
Real-time duplex voice for DeepSeek Harness: Volcengine streaming ASR/TTS, agent reply narration, barge-in, wake word, live captions. | 实时双工语音插件：火山流式 ASR/TTS、回复朗读、打断、唤醒词、实时字幕。
tangzheng202202
Bundle
dsh-voice-suite
Speech suite for DeepSeek Harness: free edge-tts page announce, speech-to-text voice input (Bailian paraformer-realtime-v2) with Alt+Q hotkey, tap/hold modes, auto-send, and stop-playback-on-record
chentao4183
Bundle
@lovstudio/dsh-video-studio
A local-first video editing workbench for DeepSeek Harness with Remotion, GSAP and pluggable ASR
lovstudio
Bundle
dsh-qwen-multimodal
DSH bundle: Qwen multimodal bridge — vision (qwen3-vl), speech-to-text (qwen3-asr), text-to-image (qwen-image), via the deepseek-vision skill scripts
wuwangmao
Bundle
dsh-doubao-voice
DSH WebUI 语音输入插件（火山引擎流式 ASR / 豆包 Seed ASR）：输入框麦克风按钮（Alt+V）→ 浏览器采集 16kHz PCM → 经宿主 WebSocket 中继到豆包流式识别 → 实时回填（跟随光标/Proma 式输出，失败兜底剪贴板）。协议实现源自 Proma 桌面端调研复刻。
Vorpal-poem
Bundle
@opensquad/dsh-voice-input
SenseVoice 语音输入插件 for DeepSeek Harness：在对话输入框旁添加麦克风按钮，录音后调用本地 SenseVoice 服务转成文本填入输入框。首次使用自动下载模型并显示进度，后端由插件自动启动。
opensquad-ai
Bundle
dsh-live-talk
Animate any photo into a responsive virtual girl. She talks, turns, smiles, and moves naturally in sync with your conversation. Low-lag, high-detail.
eddiehuang227-source
Bundle
dsh-bili-asr
B站视频脚本提取插件：解析链接，优先取字幕轨，无字幕用本地 whisper (large-v3-turbo) 转写，导出 SRT/TXT/JSON。跨平台（Windows/macOS/Linux）。
rudyz666
Bundle
@harness-flow/dsh-voice
dsh-voice — turn-based voice loop for DeepSeek Harness: pluggable Qwen / MiMo / local ASR+TTS engines, agent-driven speak/listen tools and browser PTT UI, built for interviewer presets
Harzva
Bundle
dsh-koein
Wake-word voice input for DeepSeek Harness: an always-on, low-power keyword spotter wakes the agent, then local ASR turns what you say next into a submitted message. No API key, no cloud, no typing.
Miyamiz39
Bundle
dsh-voice-input-qwen-asr
Voice input plugin (dual-face): mic button beside the composer send action, live recording bubble streaming PCM to a local Qwen3-ASR python service managed by the host, plus an ASR environment settings page (clone runtime/model repos, create venv, run server). Bilingual UI (zh/en)
jsoncode