tts

DeepSeek Harness 插件：通知出口——agent 通过桌面通知 / 中文语音播报 / 提示音主动联系用户（长任务完成、出错、呼叫用户回来）。Windows 本机零依赖。

Guide Dog for DSH — MiniMax multimodal plugin: image/video/music/speech generation & vision tools, hard-metric voice mode (host event-driven auto TTS, session-safe playback), voice input (mic → faster-whisper → composer), recorder page, two-layer settings.

DeepSeek Harness 语音双件套插件：voice_tts（edge-tts 协议免费微软神经语音合成，Sec-MS-GEC 本地 DRM 生成）/ voice_stt（OpenAI 兼容 ASR）/ voice_list。· TTS + STT for DeepSeek Harness agents.

MiniMax multimodal capability hub for DeepSeek Harness (DSH): image understanding (VLM), text/image-to-video, speech, music, audio cover, web search, quota — one mmx_multimodal model tool wrapping the mmx-cli.

Voice for DeepSeek Harness（dsh） — speech-to-text input + read-aloud TTS for text-only DeepSeek, zero API key.

Voice notes in, spoken answers out — dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), and leave walk-away narration on long headless runs. Local-first: plain audio files under ~/.dsh/voice/.