dsh-chatvoice
Browser-native voice input and AI reply read-aloud for DeepSeek Harness web.
Install
$ dsh plugin --profile web add dsh-chatvoicePlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Adds a microphone control to the chat composer for speech-to-text input with interim results.
- Adds per-assistant-message controls to read replies aloud and stop playback.
- Can automatically read newly completed assistant replies when enabled.
- Provides settings for recognition language, auto-read, voice name, and speech rate.
- Persists configuration to ~/.dsh/chatvoice.json through plugin host routes.
- Displays user-facing errors for microphone permission, unsupported browsers, insecure contexts, and recognition network failures.
Useful For
- Dictating prompts in DeepSeek Harness web chat.
- Listening to long assistant responses instead of reading them.
- Supporting Chinese-first voice interaction workflows.
- Adjusting speech language, voice, and speed from DSH settings.
Who It Fits
- DeepSeek Harness web users who prefer voice input.
- Users who want browser-based reply read-aloud without an API key.
- Chinese-speaking users, especially those using Microsoft Edge.
Documented Limitations
- Speech recognition requires a secure context such as localhost or HTTPS; LAN-IP access disables microphone input, though read-aloud remains available.
- Firefox and Safari do not support SpeechRecognition according to the repository; their voice-input control is disabled while read-aloud remains available.
- Chrome recognition may encounter network errors on some mainland China networks; the README recommends Edge.
- Edge online voices require connectivity and fall back to local system voices when offline.
- Recognition accuracy depends on the browser and system microphone.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 1 runtime, 1 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- FuzzySoul/dsh-chatvoice
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 3911aba · 2026-09-16
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 3GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-16
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Connect ChatGPT (Codex), Claude, Grok, and GitHub Copilot subscriptions to DeepSeek Harness via OAuth.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Unofficial Command Code LLM provider plugin for DeepSeek Harness with live catalogs, account rotation, and web search.
View plugin →