文件与数据插件

dsh-voice-mimo

ch1bug/dsh-voice-mimo

Xiaomi MiMo-powered voice for DeepSeek Harness: browser 🎤/🧠/🔊 UI, voice_transcribe/voice_understand/voice_speak tools, configurable voice map (preset/voicedesign/voiceclone). Fork of zhuiyueya/dsh-voice (MIT), Settings pattern from Anionex/dsh-vision-toolkit (MIT).

查看仓库

Stars: 0
Forks: 1
Issues: 4
更新: 5 天前

PROJECT TOPICS

项目标签

ai-agents deepseek deepseek-harness deepseek-harness-plugin dsh-plugin multimodal speech-to-text stt text-to-speech tts

INSTALL REFERENCE

安装参考

未验证

dsh plugin --profile web add github:ch1bug/dsh-voice-mimo

在 DSH 中安装

该命令指向仓库当前默认分支；尚无绑定当前 commit 的完整验证结果。

PROJECT README

README

⚠️ DEPRECATED — this repo is archived

dsh-voice-mimo has been absorbed into dsh-mimo-agent-tools (single-repo decision, docs/adr/0001 in that repo). No new work lands here; see the issue tracker for the migration trail (this repo #3/#4/#17, that repo #3/#4/#5).

Where everything went

What	Now lives at
🎤/🔊 Browser voice UI (mic input, read-aloud, Settings → Voice, play strips/cards)	dsh-mimo-agent-tools `./client` entry (plugin `voice`)
📄 `voice_transcribe` / 🗣️ `voice_speak` / `voice_understand` agent tools	dsh-mimo-agent-tools `./mimo` entry (tools `mimo_asr` / `mimo_speak` / `mimo_audio`)
Reusable MiMo TTS/ASR client (`ctx`-light export)	dsh-mimo-agent-tools `mimo` module export

Migration carried over all capabilities: read-aloud fix, Plugins-tab settings, manifest-faithful audio store, V2.6 default for mimo_audio (mimo-v2.5 retired upstream; ASR/TTS v2.5-series models unchanged).

Install (new repo)

dsh plugin --profile web add github:ch1bug/dsh-mimo-agent-tools

Configure the MiMo key through DSH Credentials as XIAOMI_API_KEY, then open Settings → Plugins for voice settings.

License

MIT — see LICENSE. Upstream dsh-voice (zhuiyueya) and the vision-toolkit settings pattern (Anionex) retain their copyright notices.

CLASSIFICATION EVIDENCE

分类依据

项目类型插件

功能分类文件与数据

规则置信度中

系统优先读取 GitHub Topics，再与站内分类词典和词根规则比对。当前命中： multimodal。