Synthesize local offline speech via the Piper TTS engine.
npx skills add https://github.com/Svtoo/atk-registry --skill piper-tts-skill
Please help me install this Agent Skill. Skill: Piper TTS — Skill Source: https://github.com/Svtoo/atk-registry/tree/main/plugins/piper Command: npx skills add https://github.com/Svtoo/atk-registry --skill piper-tts-skill
This Skill provides a local, offline text-to-speech (TTS) capability, allowing AI agents to narrate their actions and communicate audibly without relying on external cloud services.
speak tool for seamless integration with AI agents.Use the speak tool to narrate the text "I am about to deploy the changes."
High-intent search queries and answers about installing and using this skill.
Offline text-to-speech synthesis is enabled by running the Piper engine through a local HTTP service, exposing a speak tool for AI agent narration without external cloud dependencies.
Local TTS allows AI agents to audibly narrate intents, progress, and results during complex code refactoring, keeping users informed and engaged throughout the workflow.
An internet connection is not required for speech synthesis after setup, as Piper operates locally and offline, though voices are downloadable on demand when initially selected.
Voice selection and playback parameters for offline speech synthesis are customizable through the speak tool, supporting a wide range of downloadable voices and dynamic audio output settings.
MCP integration supports text-to-speech narration by exposing a dedicated speak tool, facilitating seamless audio communication between AI agents and users through the Piper engine.
Local offline TTS requires maintaining the Piper HTTP service and managing downloaded voice files locally, but provides fast, private speech synthesis without relying on external cloud APIs.
sentientspriteGenerate speech audio files locally using sherpa-onnx and Piper TTS models.
borealBytesConverts text to speech via ElevenLabs TTS using the sag CLI with selectable voices/models.
MuhammadUsmanGMExecute MCP calls in external scripts to minimize agent context tokens.
MOODMNKY-LLCConverts text to speech offline using sherpa-onnx runtime and voice models.