@flowingspring/dsh-voco
Persistent voice conversations for DSH with cloud speech recognition, Edge TTS, and background Agent delegation
80 results
Persistent voice conversations for DSH with cloud speech recognition, Edge TTS, and background Agent delegation
DeepSeek Harness 语音输入插件:在输入框加入麦克风按钮,用浏览器 Web Speech API 把语音实时转成文字填入输入框。
Speech capability plugin for the DeepSeek Harness (dsh) web host: a token-gated /s/api route family serving audio transcription (ASR) and synthesis (TTS) over configurable providers
DeepSeek Harness live voice preview with exact-session consent, a local synthetic demo, and one bounded manual turn
DSH Web 语音输入插件:默认使用浏览器内置 Web Speech API,也可按需下载本地模型离线识别。
Voice-to-text for DSH, powered by Whisper. One click to record, speak, and text appears in the input box. Local-first (privacy), Simplified-Chinese output, anti-hallucination, works in China without a VPN. · DSH 语音输入插件:点一下麦克风说话,文字自动进输入框。本地优先、强制简体、防幻觉、国内网络直连可用。
Text-to-speech for DeepSeek Harness: speak agent replies in the Web UI with a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak).
Offline Parakeet voice input for DeepSeek Harness
OpenRouter image, video, and speech generation as dsh tools, shipped as an out-of-tree profile bundle
视频转文字。用户发抖音分享链接(获取标题/作者/点赞等元数据),或本地视频文件(语音转写全文)时使用。抖音链接用 SSR 解析无需 Cookie。Video to text: extract metadata from Douyin share links, or transcribe speech from local video files.
DeepSeek Harness 插件:语音 + 通知出口——agent 通过云端 TTS(火山 seed-tts / 小米 MiMo V2.5,失败自动回退 SAPI)/ 桌面通知 / 提示音主动联系用户。融合 dsh-plugin-notify 的 DSH 原生深度集成与 agent-voice-mcp-minus 的云端 TTS 调优,零 Python 依赖,Windows 原生。
喵语定制:为 DSH 消息正文提供可配置的显示层文本替换(仅界面显示,不改动真实对话内容)
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。
DSH plugin: speech-to-text input via microphone or file upload, transcribed through an OpenAI-compatible /v1/audio/transcriptions endpoint.
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。
Provider-neutral full-duplex voice Agent capability for DeepSeek Harness.
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
TTS 语音播放插件:为 DSH 聊天界面添加语音朗读功能,支持配置本地 TTS 服务,每条助手消息可朗读,AI 可调用 tts-speak 工具发送语音。
DeepSeek Harness plugin: speak text with a local Kokoro TTS HTTP server and return the wav path, as the kokoro_tts tool. Ships no weights.
DSH bundle: Qwen multimodal bridge — vision (qwen3-vl), speech-to-text (qwen3-asr), text-to-image (qwen-image), via the deepseek-vision skill scripts
Optional Web UI enhancements for DeepSeek Harness
Voice chat for DSH Web: speech-to-text input (Web Speech) + auto/manual read-aloud of assistant replies (TTS) with voice/rate/pitch settings. Pure client UI, minimal Node entry.
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。
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。