AI Integration Skill

Integrate LLMs, STT, and TTS services with WebSocket audio streaming.

Updated Jan 25, 2026

Search Tags:#integration #ai #llm #tts #websocket #stt

Ready to run

npx skills add https://github.com/TikTzuki/demo-apps --skill ai-integration-skill

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: AI Integration Skill
Source: https://github.com/TikTzuki/demo-apps/tree/main/social-commerce/skills/ai-integration
Command: npx skills add https://github.com/TikTzuki/demo-apps --skill ai-integration-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill simplifies the integration of various AI services, including Large Language Models (LLMs), Text-to-Speech (TTS), and Speech-to-Text (STT), into applications.

Core Features & Use Cases

LLM Integration: Connect with powerful LLMs like Claude (Anthropic) and OpenAI (GPT-4o) for advanced text generation and conversational AI.
Speech-to-Text (STT): Convert spoken language to text using browser-based Web Speech API or the highly accurate OpenAI Whisper API.
Text-to-Speech (TTS): Synthesize speech from text using browser-based Web Speech API, ElevenLabs, or OpenAI TTS.
Real-time Audio Streaming: Facilitates live audio processing and communication via WebSockets.

Quick Start

Use the AI Integration Skill to generate a response from Claude using the provided messages and system prompt.

Frequently Asked Questions about AI Integration Skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I integrate LLM and speech-to-text services like Claude and Whisper into my application?▼

You can integrate LLM, STT, and TTS services like Claude, OpenAI, and Whisper by using a unified script that handles API connections, allowing your application to process natural language and audio inputs directly.

Does WebSocket support real-time audio streaming for TTS and STT integrations?▼

Yes, WebSocket connections support real-time audio streaming for both Text-to-Speech and Speech-to-Text, facilitating live audio processing and immediate communication between the client and AI services.

Can I use browser-based Web Speech API for STT and TTS instead of external APIs?▼

Yes, you can use the browser-based Web Speech API for both Speech-to-Text and Text-to-Speech as a native alternative, or switch to external services like ElevenLabs and OpenAI TTS for synthesized audio.

What is the best way to connect OpenAI GPT-4o with ElevenLabs for a voice assistant?▼

The best way to connect GPT-4o with ElevenLabs is through a unified AI integration script that passes LLM text generation outputs directly into the TTS API, enabling seamless conversational AI voice assistant workflows.

How do I convert spoken language to text using the OpenAI Whisper API?▼

You convert spoken language to text using the OpenAI Whisper API by routing your audio input through an integration script that handles the STT API requests, returning accurate text transcriptions for processing.