Integrate streaming voice capabilities into agentic frameworks with Cloudflare Workers AI.
npx skills add https://github.com/northclock/ayjnt --skill ayjnt-voice
Please help me install this Agent Skill. Skill: ayjnt-voice Source: https://github.com/northclock/ayjnt/tree/main/.claude/skills/ayjnt-voice Command: npx skills add https://github.com/northclock/ayjnt --skill ayjnt-voice
This skill simplifies the complex integration of real-time speech-to-text and text-to-speech capabilities into agentic workflows, removing the need for manual WebSocket and audio stream management.
Use the ayjnt-voice skill to add a voice interface to my existing chat agent by wrapping the agent class with the withVoice mixin and configuring the STT and TTS providers.
High-intent search queries and answers about installing and using this skill.
You can add streaming voice by wrapping your agent class with the withVoice mixin to enable bi-directional audio streaming over WebSockets. This integrates Workers AI for low-latency speech-to-text and text-to-speech processing without manual stream management.
Managing WebSocket audio streams is handled automatically by the withVoice mixin. It provides STT and TTS lifecycle hooks and typed client-side hooks, removing the need for manual WebSocket and audio stream management during real-time interactions.
Yes, the @cloudflare/voice package is required to build streaming voice agents. It provides the necessary Workers AI pipeline connections and the withVoice mixin structure needed to manage audio streams and transcript processing.
Yes, you can use Workers AI for speech-to-text and text-to-speech in a conversational agent. The skill seamlessly connects to Workers AI STT and TTS providers to listen to user input, process it, and respond with synthesized speech in real-time.
The withVoice mixin handles the STT and TTS lifecycle by providing specific lifecycle hooks within a compatible agent class structure. This facilitates interactive voice assistant development by automatically managing audio streams and transcript processing over WebSockets.
charl-krugerControl headless Chrome in Cloudflare Workers via CDP WebSocket.
gman-roboticsGenerates MP3 podcast audio and markdown transcripts from text using Volcengine TTS API.
FutureAtomsBuild real-time audio and video apps via WebSocket streaming with Gemini API.
TikTzukiIntegrate LLMs, STT, and TTS services with WebSocket audio streaming.
