xby-speech-synthesis
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-speech-synthesis
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-speech-synthesis in your DeepSeek Harness terminal to install; the source code is available at https://github.com/xby-skill/xby-speech-synthesis
About this plugin
Need to turn a block of text into natural, high-quality speech without leaving your chat window? xby-speech-synthesis is a DeepSeek Harness plugin built on the Microsoft Edge speech synthesis engine, making text-to-speech a simple tool call right within your conversation.
The plugin offers two core capabilities. Multilingual speech generation with multi-role conversation support: synthesize lines for different characters sequentially and have them automatically merged into a single complete audio track. Persistent API key management: set the key once in chat and it is saved automatically, surviving restarts so you never have to reconfigure.
Whether you are prototyping multi-character voice demos, adding narration to content drafts, or simply want a passage read aloud mid-conversation, this plugin saves you a window switch and an extra step.
Use Cases
- Invoke a tool call mid-chat to turn a text passage into natural speech
- Synthesize lines for multiple characters sequentially and merge them into one audio track
- Quickly produce multilingual voice demos or content narration prototypes
Best For
- Developers who need fast speech generation without leaving their chat
- Content creators building multi-character voice demos
- AI engineers who want to invoke TTS directly within a conversation
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.