dsh-cyberdog-speech-sherpa
DeepSeek Harness 本地离线语音插件:STT 语音识别 + TTS 语音合成 + WebUI 按住说话(Sherpa-ONNX)
70 results
DeepSeek Harness 本地离线语音插件:STT 语音识别 + TTS 语音合成 + WebUI 按住说话(Sherpa-ONNX)
Local-first, full-duplex voice for DeepSeek Harness, orchestrated by Muxiva
Voice assistant plugin for dsh web: hands-free wake phrase, dictation, voice edit commands, and Chinese TTS.
Local IndexTTS 2.5 and GPT-SoVITS sentence-level speech synthesis and playback for DeepSeek Harness
个人语音通话助手:专属工作区/会话(自动创建、跨重启保持)、悬浮球通话面板、FunASR 流式/HTTP 语音识别、云端 TTS 语音回复、唤醒词通话模式(可配置唤醒词/休眠时长,建议本地 ASR)、子代理任务分发与进度跟踪。持久化安装,重启后仍在「设置 → 插件」中可见。
Chat with, monitor, and approve your DSH agents from WeChat — an iLink gateway + conversation node bundle for DeepSeek Harness
Voice practice mode for the DSH web app: bilingual (中文 / English) conversation output plus read-aloud (TTS) and speech input (STT). Adds a 语音交流 dialog-mode toggle to the composer.
给 DeepSeek Harness(DSH / DeepSeek Hermes)加语音能力的社区插件:输入框语音输入(可配快捷键)+ 回答朗读(微软 Edge 神经网络音色,可换音色、可试听),无需 API Key。
App-free mobile voice calls with existing DeepSeek Harness sessions
Session-scoped full-duplex voice assistant with tool-controlled drafting and Agent submission for DeepSeek Harness.
Voice input (Web Speech API) and read-aloud (speechSynthesis) for the DeepSeek Harness web GUI — DSH 语音输入 + 回复朗读套件
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).
Speech plugin for DeepSeek Harness: per-message speak button, composer voice input, and auto-announce toggle, over cloud TTS/ASR with Web Speech API fallback
队长来电(captain-call):AgentTeams 队员完成任务时,桌面助手 GINKA 替 Daisy 队长接听来电,语音汇报'是谁、是否按要求准时完成';点语音回复即直接申请麦克风,与真实队员语音办公对话。
聊天框语音输入按钮 for DeepSeek Harness: 点击麦克风说话,多引擎转写(智谱 GLM-ASR-2512 / 本地 faster-whisper / Gemini / OpenAI)自动填入输入框。一个按钮,所见即所得。
Dub video and audio into 10 languages with voice cloning, from a DeepSeek Harness agent — one tool call, local file or URL
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
Telegram messenger bridge for DeepSeek Harness: sessions, steer, homes, inline asks, notify bridge, and optional TTS voice notes.
语音朗读(MiniMax / OpenAI 兼容 TTS,服务商与音色自选)——每条回复旁的朗读按钮、输入框自动朗读开关、设置页自选服务商与音色。零构建,纯 JS。
MiniMax speech-to-text (asr-1.0) and text-to-speech (speech-2.8-hd) as a global DeepSeek Harness plugin: a transcribe_audio tool, an announce_speech tool, a settings card, composer voice input, spoken turn announcements, and handsfree conversation.
Voice conversation mode for the DeepSeek Harness Web GUI: mic input with auto-submit, streaming spoken readout of replies, and a hands-free multi-turn loop with barge-in.
Plays a vanilla Minecraft villager "hmm" whenever the model hums inside its reasoning chain.
DSH 对话语音/音效提醒插件:每个 turn 结束自动播报「完成」,工具报错或回合失败时播「失败」,并在 DSH 设置页提供独立的「语音播报」分区。开箱即用——默认「音效」模式内置 20 个音效(提醒 10 + 大自然 10),不需要 API Key、不需要自备音频;想用自己的声音可用火山「声音复刻」克隆音色,一键生成三条播报语音(克隆/预设双路由、批量导入、试合验证)。走 winmm/waveOut 原样播放,绝不改动系统音量或静音状态。仅 Windows。| DSH voice/sound alert plugin: speaks or plays a cue at the end of every turn and plays a failure cue when a tool call or turn errors, with its own section in the DSH settings page. Works out of the box — the default effect mode ships 20 built-in sounds (10 alert chimes + 10 nature) with no API key and no audio files; an optional Volcengine voice-clone route can generate the three announcement clips in one click. Plays through winmm/waveOut as-is and never touches the system volume or mute state. Windows only.
Vibe coding时的好伴侣