@flowingspring/dsh-voco
Persistent voice conversations for DSH with cloud speech recognition, Edge TTS, and background Agent delegation
32 results
Persistent voice conversations for DSH with cloud speech recognition, Edge TTS, and background Agent delegation
DSH KITT — Spanish-first voice for the DeepSeek Harness web UI: hands-free conversation, push-to-talk (Whisper), read-aloud replies, and a floating overlay window with global hotkeys. · DSH KITT 语音:为 DeepSeek Harness 打造的语音插件——免提对话、按键说话(Whisper)、朗读回复,以及带全局快捷键的悬浮窗;界面支持中文、英文和西班牙语。
Voice for DeepSeek Harness backed by Xiaomi MiMo: browser-native 🎤/🔊 UI (MiMo TTS read-aloud) + voice_transcribe/voice_speak calling MiMo ASR/TTS directly, with a configurable voice map and in-conversation speech strips. Fork of zhuiyueya/dsh-voice (MIT).
Voice-feedback plugin for DeepSeek Harness: a speak tool, readReplies narration, an LLM verbalizer pass, per-session voices, chimes, a monitoring panel, and a native macOS floating pet. zh/en i18n.
A speaker button beside the Like button: read any assistant reply aloud with the browser's built-in speech engine, with speed and voice control. · 在点赞旁加一个小喇叭,朗读 DSH 的回复,支持倍速与音色。
Give your DSH agent a voice: speaks your reports aloud through your speakers. System voices work out of the box; character voices need no GPT-SoVITS install and no training.
DSH 里用 DeepSeek 官方朗读音色朗读对话、导出音频,并提供「文本进、音频出」的接口与工具。宿主半走 DS 官方 TTS(ticket + wss),文本投递由真实浏览器经 CDP 完成(不逆向 PoW、不伪装 TLS 指纹)。
Full-duplex voice plugin for DeepSeek Harness: local zipformer2 streaming ASR (no API key) → editable draft; Edge TTS or local VITS / Kokoro read-aloud with live captions; true barge-in; hardened HTTP surface + model SHA256 pinning; compatible with all ds