← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-tts-live

Multi-provider text-to-speech plugin for DeepSeek Harness with live sentence streaming and barge-in.

UI & ProductivityDeveloper ToolsBrowser & WebSkills & Workflows
0GitHub Stars0ForksUpdated2026-09-24

Install

$ dsh plugin --profile web add file:/path/to/dsh-tts-<version>.tgz

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
dsh-tts-live is an enhanced fork of @goodandready/dsh-tts that delivers live, sentence-level text-to-speech synthesis directly to the DeepSeek Harness Web UI. It hooks into the token-level assistant stream to synthesize and play sentences as soon as they are completed, reducing perceived voice latency. The plugin supports fallback chains across 18 cloud and local TTS providers, host-side barge-in cancellation, smart IT dictionary pronunciations, and subagent persona voices.

Key Capabilities

  • Live sentence-level speech streaming hooked into process-local assistant streams
  • Multi-provider fallback chains supporting cloud and offline engines (Edge TTS, Piper, eSpeak, OpenAI, ElevenLabs, etc.)
  • Host-side barge-in cancellation via POST /dsh-tts/bargein and AudioWorklet PCM playback
  • Built-in IT terminology pronunciation dictionary and markdown scrubbing (tables, code blocks)
  • Subagent voice overrides and messenger gateway audio generation

Useful For

  • Speaking assistant responses in real time with minimal latency inside DeepSeek Harness Web UI
  • Configuring customized voices for different subagent roles like coder or reviewer
  • Generating voice notes for messenger integrations or offline audio clip exports

Who It Fits

  • DeepSeek Harness users wanting low-latency voice interaction and duplex conversations
  • Developers needing offline or multi-provider speech synthesis fallback chains

Documented Limitations

  • Local TTS inference shares GPU resources with local LLMs, which can cause scheduling contention
  • Does not decrease model time-to-first-token (TTFT)
  • Kokoro-82M and F5-TTS neural runtimes are not bundled and fail honestly without an external runtime wired
  • Inline code scrubbing may cause audible pauses in code-heavy sentences

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.

Dependency Counts

package.json declares 0 runtime, 0 development, 6 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

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

Source repository
YevheniiMiachyn/dsh-tts-live
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
ac9aafd · 2026-09-27

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
2026-09-24
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