Back to Marketplace
LifestylePlugin

dsh-voice

haoku123/dsh-voice

dsh-voice is a tool for DeepSeek Harness. Full-duplex voice plugin for DeepSeek Harness: mic → SenseVoice ASR (sherpa-onnx) → LLM → Edge TTS with true barge-in. Full-duplex voice plugin: microphone voice input, SenseVoice local recognition (Simplified Chinese + punctuation + ITN), streaming TTS playback, supports voice interruption. Zero API key.

haoku123/dsh-voice Screenshot preview
Stars
5
Forks
1
Issues
0
Update
40 days

REVIEW SCORECARD

Review Scorecard

7.6/10Average
License compliance9.0
Engineering quality5.6
Content completeness7.0
Repository scale7.0
Maintenance activity8.0

✓ No risk detected · Automated scan results are for reference only, not an official endorsement

AI DEEP REVIEW

Worth AI Review

8.0/10Recommended

A well-documented, actively maintained full-duplex voice plugin with local ASR and no API keys, worth installing.

Code quality8

README documents a clear modular architecture (src/aec.ts, SentenceSegmenter, TtsQueue), lossless stream tap, epoch-based cancellation, and a prefetch script, though no test suite or CI is mentioned.

Security7

Runs ASR locally via sherpa-onnx with zero API keys and only downloads models from configurable HuggingFace mirrors into a local cache, but the README gives no explicit permission or sandboxing details.

Utility9

Solves a real pain point by adding true barge-in voice input/output to DeepSeek Harness with CN-native SenseVoice ASR, live captions, and press-to-talk gestures.

Maintenance8

Last updated 2026-08-23 with an active v0.7.0 release, MIT license, and not archived, indicating ongoing development.

Documentation8

README covers install command, config YAML, API routes, gesture table, architecture diagram, and demo GIF, giving users enough to install and operate it.

Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.

PROJECT READMEREADMEExpandCollapse

Loading GitHub README...

INSTALL REFERENCE

Install reference

Structure check pending
dsh plugin --profile web add <repo-url-or-path>

This command was extracted from an explicit README install reference and is display-only; the DSH host will not execute it automatically.

PROJECT TOPICS

Project topics

VALIDATION LADDER

Validation progress

Structure check pending
01Store discoveryPassed
02ClassificationPassed
03Structure checkPending
04Sandbox validationPending

FAQ

Frequently Asked Questions

What is dsh-voice used for?

Full-duplex voice plugin for DeepSeek Harness: mic → SenseVoice ASR (sherpa-onnx) → LLM → Edge TTS with true barge-in. Full-duplex voice plugin: microphone voice input, SenseVoice local recognition (Simplified Chinese +

How popular is dsh-voice?

dsh-voice has 5 stars and 1 forks on GitHub, last updated 2026-08-23.

What license does dsh-voice use?

dsh-voice is distributed under the MIT license.

Is dsh-voice compatible with DeepSeek Harness?

dsh-voice is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.

CLASSIFICATION EVIDENCE

Classification evidence

Project typePlugin
Feature categoryLifestyle
Rule confidenceHigh

The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:sensevoice、voice、voice-mode。