dsh-voice-mode
Voice Mode
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
The plugin will be installed here. Keep web if you are unsure.
npx -y @deepseek-ai/dsh plugin --profile web add dsh-voice-mode@0.7.24Compatibility and provenance
Voice Mode is published as dsh-voice-mode and currently resolves to version 0.7.24. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.
- DSH compatibility
- *
- Runtime surfaces
- web
- Release source
- npm
- Registry updated
Versions
0.7.24stable
0.7.23stable
0.7.22stable
Show 35 more versionsCollapse versions
0.7.21stable
0.7.20stable
0.7.19stable
0.7.18stable
0.7.17stable
0.7.16stable
0.7.15stable
0.7.14stable
0.7.13stable
0.7.12stable
0.7.11stable
0.7.10stable
0.7.9stable
0.7.8stable
0.7.7stable
0.7.6stable
0.7.5stable
0.7.4stable