AtropinolTT/dsh-guide-dog
AtropinolTT★ 1JavaScript最后同步: 2026-08-15
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.
README 摘要
Guide Dog for DSH, powered by MiniMax A dynamic Cordis plugin that gives DeepSeek Harness multimodal superpowers through the mmx CLI (MiniMax): - Eyes for DeepSeek — MiniMax VLM ( guide dog vision / guide dog inspect ) describes images, so a model with no native vision input (e.g. DeepSeek) can still review frontend designs, figures, screenshots, and generated images. - Hands for generation — images ( image-01 ), video ( MiniMax-H3 / Hailuo), speech (MiniMax TTS), music ( music-3.0 ), text ( MiniMax-M3 ), and web search. - Web UI preview & playback — every generated file is served same-origin at /guide-dog/media/ and rendered inline in the conversation tool cards ( , , ), plus a Guide Dog settings page with auth status, a speak tester, and a recent-media gallery. - Skill integration — guide dog speak reuses your existing audio-conversation and speech-mmx skill pipelines (text transform, CJK auto-detect, per-language voices, host playback), and falls back to raw mmx speech synthesize when the skill scripts are absent. - Automatic invocation — a mounted system-prompt section ( guide-dog-vision , order 110) tells the agent to auto-invoke the inspection tools for any job needing visual…
在 GitHub 查看完整 README →