Orchestrate offline realtime voice pipelines with local STT, LLM, and TTS.
npx skills add https://github.com/J4Joshua/manuaI --skill livekit-agents-j4joshua
Please help me install this Agent Skill. Skill: livekit-agents Source: https://github.com/J4Joshua/manuaI/tree/main/.agents/skills/livekit-agents Command: npx skills add https://github.com/J4Joshua/manuaI --skill livekit-agents-j4joshua
This Skill solves the complexity of building a reliable offline voice copilot by coordinating realtime audio transport, local speech recognition, local reasoning, and speech synthesis without cloud dependencies.
Use the livekit-agents skill to configure a fully offline voice agent pipeline with local STT, LLM, TTS, push-to-talk controls, and SOP-aware screen updates.
High-intent search queries and answers about installing and using this skill.
Build an offline voice agent by orchestrating local speech recognition, reasoning, and text to speech through LiveKit Agents, connecting Whisper STT, Qwen LLM, and Kokoro or Piper TTS pipelines without cloud dependencies.
Yes, you can use local Whisper and Qwen models for air-gapped voice interfaces by connecting self-hosted LiveKit Agents with local inference services to enable offline speech pipelines.
Implement push-to-talk workflows with realtime streaming by configuring sentence-level streaming, transcript delivery, and safety states within the LiveKit Agents voice pipeline orchestration.
Create a factory-floor voice assistant by configuring a realtime operator interaction pipeline where spoken machine faults trigger grounded SOP context retrieval, delivering cited responses through local text to speech.
Yes, the offline voice agent approach works without internet connectivity by relying entirely on local inference services for speech recognition, language model reasoning, and speech synthesis.
Limitations of local AI models for realtime voice orchestration include requiring sufficient local compute for Whisper STT and Qwen LLM inference, and needing self-hosted LiveKit Agents infrastructure to maintain air-gapped deployments.
FutureAtomsIntegrate Google AI services with LiveKit for real-time voice and chat applications.
J4JoshuaGenerate grounded answers from retrieved SOP chunks using local Qwen2.5-Instruct.
jokken79Develop real-time voice AI applications using OpenAI Realtime API, Deepgram, ElevenLabs, and LiveKit.
jx1100370217Configure local TTS and STT voice capabilities for OpenClaw.
