ArchivedThis repository is archived and may no longer be actively maintained.
DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

kepos-speech

Dual-provider Chinese tagged text-to-speech plugin for DeepSeek Harness Web supporting Alibaba and ByteDance.

UI & ProductivityBrowser & WebRemote Execution
0GitHub Stars0ForksUpdated2026-09-04

Install

$ dsh plugin --profile <profile> add @lamplitisles/kepos-speech

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
kepos-tts is a DeepSeek Harness plugin bundle that brings Chinese text-to-speech capabilities to DSH Web sessions. It detects [[tts:text]]...[[/tts:text]] tagged blocks in finalized assistant replies, prepares MP3 audio via Alibaba DashScope (Qwen3-TTS Flash) or ByteDance Volcengine (seed-tts-2.0), caches the audio in the workspace, and renders a native browser audio player in place of the tag.

Key Capabilities

  • Parses [[tts:text]] tags in finalized assistant responses and converts text into spoken MP3 audio
  • Integrates with Alibaba DashScope (Qwen3-TTS Flash) and ByteDance Volcengine (seed-tts-2.0)
  • Replaces tags in the browser chat interface with a native HTML5 audio player
  • Persists generated audio files keyed by SHA-256 in the session workspace directory (.dsh/kepos-tts/audio/)
  • Provides a dedicated settings card in DSH Web for provider selection, custom Voice IDs, and API key management

Useful For

  • Listening to synthesized voice readings of assistant responses in Chinese
  • Adding natural speech playback for conversational voice agents in DSH Web
  • Generating and caching reusable speech audio artifacts for AI session transcripts

Who It Fits

  • DeepSeek Harness Web users needing speech output for Chinese text
  • Developers building voice-enabled assistant workflows on DSH
  • Users with Alibaba DashScope or ByteDance Volcengine TTS API credentials

Documented Limitations

  • Only triggers on finalized messages with exact [[tts:text]] tag syntax; malformed tags remain visible text
  • Requires an absolute session workspace for local audio file caching
  • Settings card requires local loopback or ready Host scope; unavailable in remote memory-backed scopes
  • Pinned to DSH 0.1.2-alpha.3 contract family and APIs

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
LamplitIsles/kepos-speech
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin Bundle
Source checked
06f5960 · 2026-09-12

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
0GitHub stars
Forks
0
Open issues
0
Last commit
2026-09-04
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