dsh-voice
Run the following command in DeepSeek Harness:
dsh plugin install STARDUSTLC666/dsh-voice
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, you can install this plugin by running the command `dsh plugin install STARDUSTLC666/dsh-voice` or by visiting the GitHub repository at https://github.com/STARDUSTLC666/dsh-voice.
About this plugin
In AI agent development, text interaction is foundational, but the lack of voice capabilities often creates a bottleneck, preventing natural user dialogue and limiting accessibility and application scenarios. The dsh-voice plugin is designed to solve this by offering a comprehensive voice suite: voice_tts leverages Microsoft's edge-tts protocol to convert text into speech for free and without limits, featuring over 22 natural-sounding voices; voice_stt enables efficient speech-to-text using OpenAI-compatible ASR interfaces, allowing agents to understand spoken commands. Additionally, the voice_list tool simplifies voice selection. This plugin is perfect for developers, AI enthusiasts, and projects building intelligent assistants or voice-enabled applications on the DSH platform. Whether you need an agent that can read out text or process voice inputs, dsh-voice provides powerful, cost-effective solutions with zero TTS expenses and flexible STT options, truly enabling agents to speak and understand voice.
Use Cases
- Adding natural voice replies to chatbots
- Developing voice-controlled smart assistant apps
- Automating voice content generation for podcasts or audiobooks
Best For
- AI application developers and voice tech enthusiasts
- Engineers building interactive voice systems
- Content creators and educators needing voice features
Related Plugins
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.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.