Back to Marketplace
LifestylePlugin

dsh-voice

Jesse-njx/dsh-voice

dsh-voice is a tool for DeepSeek Harness. Voice notes in, spoken answers out — dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), and leave walk-away narration on long headless runs. Local-first: plain audio files under ~/.dsh/voice/.

Jesse-njx/dsh-voice Screenshot preview
Stars
4
Forks
0
Issues
0
Update
49 days

REVIEW SCORECARD

Review Scorecard

7.5/10Average
License compliance9.0
Engineering quality5.4
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

8.4/10Recommended

A well-documented, local-first voice plugin for DSH that adds dictation and narration without owning an audio pipeline.

Code quality8

README describes a thin layer over existing ctx.shell/ctx.jobs/ctx.settings seams with a unit-testable file-write seam and a fake backend, but no CI or test files are visible in the provided info.

Security8

Local-first design keeps audio as plain files under ~/.dsh/voice, cloud backends are never auto-selected, and the OpenAI key is read via the standard OPENAI_API_KEY credential seam rather than stored in config.

Utility9

Solves two concrete terminal-agent pain points — dictating instructions while away from the keyboard and hearing replies during long headless runs — via transcribe, speak, and a /voice toggle.

Maintenance8

Last updated 2026-08-13, not archived, MIT-licensed, and the README shows an actively evolving v0.1 design with explicit event schema and backend selection logic.

Documentation9

README covers install command, full YAML config with defaults, both tool signatures, the voice/note event table, /voice subcommands, and backend options, though the backend section is truncated mid-sentence.

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 @dsh-voice/bundle

This command passed the install-plan safety checks and can be executed by the DSH host. Validation is not a security audit or official endorsement.

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?

Voice notes in, spoken answers out — dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), and leave walk-away narration on long headless runs. Local-first: plain audio files u

How popular is dsh-voice?

dsh-voice has 4 stars and 0 forks on GitHub, last updated 2026-08-13.

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 confidenceMedium

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