Convert text responses into audible speech via platform TTS backends.
npx skills add https://github.com/cyzus/suzent --skill speech-cyzus
Please help me install this Agent Skill. Skill: speech Source: https://github.com/cyzus/suzent/tree/main/skills/speech Command: npx skills add https://github.com/cyzus/suzent --skill speech-cyzus
The Speech skill removes the barrier between text-based agent responses and audible output, enabling agents to communicate verbally for greetings, alerts, and progress updates to users who prefer or require spoken feedback.
Use the SpeakTool to speak the phrase Hello, how can I help you today?
High-intent search queries and answers about installing and using this skill.
Text-to-speech functionality converts agent text responses into audible speech for conversational interactions. It handles natural language inputs and integrates with platform TTS backends to provide verbal greetings, alerts, and progress updates.
Yes, text-to-speech supports accessibility scenarios by providing verbal alerts and status updates. It enables agents to deliver spoken notifications and personality-driven greetings, improving engagement for users requiring audible feedback.
You can announce task completion by invoking text-to-speech with a short message. This provides brief spoken summaries of outcomes and progress updates, allowing agents to verbally notify users when long processes finish.
Yes, the text-to-speech feature handles natural language text inputs for simple invocation with short messages. It processes natural language text and converts it into audible speech without exposing sensitive data.
Simple text-to-speech is designed for short messages like greetings and brief summaries. It applies to conversational agents, notifications, and accessibility scenarios, but may not suit long-form text or complex verbal interactions.
rgbkrkTranscribe speech and synthesize text with Rust and candle.
matt-fell-aiDispatch text-to-speech to an external provider via a speak function and CLI.
MohabsmarAnalyze images and respond conversationally using the z-ai-web-dev-sdk.
inference-shConvert text into speech using multiple TTS models like Kokoro TTS.
