DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-voice-ai-girlfriend-plugin

A DeepSeek Harness web plugin for microphone input, streamed TTS replies, an animated companion window, and QQ chat integration.

Developer ToolsBrowser & Web
8GitHub Stars3ForksUpdated2026-09-13

Install

$ dsh plugin --profile web add github:beiyege-01/dsh-voice-ai-girlfriend-plugin

Plugin 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.

source-grounded
This installable DeepSeek Harness browser plugin adds a voice-oriented companion interface to conversations. It uses a separately deployed local voice bridge for FunASR speech recognition and Qwen3-TTS speech output, and optionally connects QQ through NapCatQQ.

Key Capabilities

  • Captures microphone speech and sends it to a voice bridge for FunASR Chinese speech recognition.
  • Injects recognized speech into DeepSeek Harness conversations with continuous listening and automatic endpointing.
  • Reads assistant replies aloud sentence by sentence through streamed Qwen3-TTS.
  • Provides interrupt or queued speech behavior for replies.
  • Adds a right-side animated digital-human companion window with idle and speaking video states.
  • Displays a DeepSeek balance badge in the stats row and provides a five-state microphone control.
  • Supports two-way QQ messaging, including injecting QQ messages and sending reply text, voice, and images through NapCat.

Useful For

  • Using spoken Chinese input in DeepSeek Harness web conversations.
  • Listening to assistant responses through synthesized speech.
  • Building a companion-style conversational interface with custom animation assets.
  • Relaying conversations between DeepSeek Harness and QQ.

Who It Fits

  • DeepSeek Harness web-profile users.
  • Users able to run the companion voice bridge locally.
  • Users operating NapCatQQ who want QQ conversation relay.

Documented Limitations

  • Speech recognition and TTS require the separate voice bridge repository and its Python services, models, and setup.
  • QQ two-way chat requires NapCatQQ.
  • The default voice bridge endpoint is http://127.0.0.1:8765, though it can be changed through localStorage key s2s.voice.bridge.
  • Digital-human idle and speaking video assets must be supplied by the user.
  • Git-based installation may require allowing esbuild build scripts in pnpm ≥10.

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

No automated security signals have been published yet.

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
beiyege-01/dsh-voice-ai-girlfriend-plugin
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
b0ac0fe · 2026-09-19

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
8GitHub stars
Forks
3
Open issues
0
Last commit
2026-09-13
Last release
No release detected
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app