dsh-syllable
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-syllable
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-syllable in your DeepSeek Harness terminal to install the plugin; the full source repository is at https://github.com/uckkk/dsh-syllable .
About this plugin
Estimating the syllable count of a text passage is a small yet frequently needed task in model-inference sessions—whether you are planning rhythm for speech output, checking meter for creative writing, or simply need a quick count mid-conversation. dsh-syllable plugs into DeepSeek Harness as an inference tool, so you can invoke it right inside the session without spinning up a separate service.
The entire plugin is implemented in pure Node.js with zero network dependencies—no external API calls, no third-party runtimes. Once installed it runs fully offline, keeping your inference pipeline deterministic and free from the fragility of remote services.
If you are building speech-related inference pipelines, analyzing rhythm in creative text, or just want a lightweight, zero-maintenance way to get syllable counts during a session, dsh-syllable is a clean, MIT-licensed option that simply gets out of the way.
Use Cases
- Estimate syllable counts to aid prosody planning in speech synthesis pipelines
- Check syllable rhythm of poetry or lyrics during a creative writing session
- Count syllables in any text in a fully offline environment
Best For
- Developers building speech-related inference pipelines
- AI engineers who need lightweight syllable counts mid-session
- Plugin users who prefer pure-local, zero-network-dependency tools
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.