Models & MCPPlugin
dsh-voice-ru
ripls56
Local Russian speech-to-text provider for DeepSeek Harness voice input: NVIDIA Nemotron 3.5 ASR 0.6B (GGUF) on transcribe.cpp. Model and native runtime download on first use, sha256-verified.
Structure check pending
asrdeepseek-harnessdshdsh-plugin