Okeysir198

Build self-hosted TTS APIs using HuggingFace models (Parler-TTS, F5-TTS, XTTS-v2) and create LiveKit voice agent plugins with streaming support. Use when creating production-ready text-to-speech systems that need: (1) Self-hosted TTS with full control, (2) LiveKit voice agent integration, (3) Streaming audio for low-latency conversations, (4) Custom voice characteristics, (5) Cost-effective alternatives to cloud TTS providers like ElevenLabs or Google TTS.

Build self-hosted speech-to-text APIs using Hugging Face models (Whisper, Wav2Vec2) and create LiveKit voice agent plugins. Use when building STT infrastructure, creating custom LiveKit plugins, deploying self-hosted transcription services, or integrating Whisper/HF models with LiveKit agents. Includes FastAPI server templates, LiveKit plugin implementation, model selection guides, and production deployment patterns.

Guide for creating effective prompts and instructions for LiveKit voice agents. Use when building conversational AI agents with the LiveKit Agents framework, including (1) Creating new voice agent prompts from scratch, (2) Improving existing agent instructions, (3) Optimizing prompts for text-to-speech output, (4) Integrating tool/function calling capabilities, (5) Building multi-agent systems with handoffs, (6) Ensuring voice-friendly formatting and brevity for natural conversations, (7) Iteratively improving prompts based on testing and feedback, (8) Building industry-specific agents (debt collection, healthcare, banking, customer service, front desk).

Comprehensive guide for building functional tools for LiveKit voice agents using the @function_tool decorator. Use when creating tools for LiveKit agents to enable capabilities like API calls, database queries, multi-agent coordination, or any external integrations. Covers tool design, RunContext handling, interruption patterns, parameter documentation, testing, and production best practices.

Build and review production-grade web and mobile frontends using LiveKit with Next.js. Covers real-time video/audio/data communication, WebRTC connections, track management, and best practices for LiveKit React components.

Guide for building production-ready LiveKit voice AI agents with multi-agent workflows and intelligent handoffs. Use when creating real-time voice agents that need to transfer control between specialized agents, implement supervisor escalation, or build complex conversational systems.

Build and deploy self-hosted Text-to-Speech API using MeloTTS from Hugging Face and create a LiveKit plugin for voice agents. Use this skill when building TTS systems, LiveKit voice agents, or self-hosted speech synthesis solutions.

This skill should be used when the user asks to "prepare training data", "build a training dataset", "merge datasets for a CV model", "audit label quality", "check dataset labels", "curate training set", "create 00_data_preparation.yaml", "run annotation QA", or wants to turn raw/ folders into a training_ready/ split in this cv-pipeline repo. Also triggers on mentions of p00_data_prep, p02_annotation_qa, p01_auto_annotate, SAM3 label verification, or label grading.

Use when the user asks to "test the full pipeline", "run an end-to-end pipeline test", "smoke test the whole pipeline", "pipeline regression check", "verify every step p00..p10 works", or mentions exercising the cv-pipeline against raw unlabeled images. Orchestrates the canonical tests/test_p12_raw_pipeline.py (which covers p01→p02→p04 LS roundtrip→p00 merge+split→p05→p06→p07 HPO→p08→p09→p10 in order) plus a Playwright MCP sanity pass against Label Studio. Never skips stages, enforces services up-front, honors short Bash timeouts with background polling, and emits a markdown report.