skills.rest
AmirEmad11
AmirEmad11COMMUNITY
Explore all skills by this author →
GitHub

ai-integrations-openai

Integrate OpenAI chat, voice, and image APIs via Replit AI Integrations proxy.

Updated Apr 20, 2026
Search Tags:#typescript#ai integration#streaming#openai#gpt#replit#voice chat
One-click install
npx skills add https://github.com/AmirEmad11/instabot --skill ai-integrations-openai-amiremad11
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-integrations-openai
Source: https://github.com/AmirEmad11/instabot/tree/main/.local/skills/ai-integrations-openai
Command: npx skills add https://github.com/AmirEmad11/instabot --skill ai-integrations-openai-amiremad11

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, p-limit, p-retry, and includes references (resource) components.

What problem does it solve? Adding OpenAI capabilities to a JavaScript/TypeScript app normally requires managing API keys, writing boilerplate for streaming chat, voice, and image endpoints, and wiring up database persistence. This Skill provisions OpenAI access through the Replit AI Integrations proxy with auto-configured environment variables and provides ready-made server modules, React hooks, and database schemas. ## Core Features & Use Cases - Streaming Text Chat: SSE-based chat completions with gpt-5.2, persisted to Drizzle conversations/messages tables. - Speech-to-Speech Voice Chat: gpt-audio voice streaming with React hooks for recording, playback, and SSE parsing, plus ffmpeg-based audio format conversion. - Image Generation & Editing: gpt-image-1 helpers returning base64 image buffers. - Batch Processing: Rate-limited, retrying batch utilities for high-volume LLM workloads. - Use Case: Build a customer support voice chatbot by provisioning the integration, copying the template packages, adding the OpenAPI spec entries, and wiring the voice-messages endpoint with the provided React voice stream hooks. ## Quick Start Set up the OpenAI AI integration in my project and build a streaming chat endpoint with conversation history stored in the database.

Frequently Asked Questions about ai-integrations-openai

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

FAQPage Schema
How do I add OpenAI chat to a TypeScript app without an API key?▼

Use the Replit AI Integrations proxy by calling setupReplitAIIntegrations with the openai provider slug. It automatically sets AI_INTEGRATIONS_OPENAI_BASE_URL and AI_INTEGRATIONS_OPENAI_API_KEY environment variables, so the OpenAI SDK works without you supplying a key.

How do I build a streaming voice chat with gpt-audio?▼

Use the voiceChatStream server function with the useVoiceRecorder and useVoiceStream React hooks. Convert browser WebM recordings to WAV with ffmpeg before sending, and stream transcript and PCM16 audio chunks back over SSE.

Which OpenAI models are available through Replit AI Integrations?▼

Supported models include gpt-5.2 for general tasks, gpt-5.3-codex for coding, gpt-5-mini and gpt-5-nano for high-volume work, o4-mini and o3 for reasoning, gpt-image-1 for images, gpt-audio for speech-to-speech, and gpt-4o-mini-transcribe for transcription. Unlisted models are not available.

Does the OpenAI integration support embeddings or fine-tuning?▼

No. The embeddings API, fine-tuning API, files API, image variations, video inputs and outputs, and the speech API are not supported. For those use cases, use OpenAI directly with your own API key or another integration.

Why does max_tokens fail with gpt-5 models?▼

gpt-5 and newer models do not support the max_tokens parameter. Use max_completion_tokens instead to cap output length, and note that temperature cannot be changed from its default of 1 on these models.

When should I use ElevenLabs instead of OpenAI for voice features?▼

Use ElevenLabs for interactive, low-latency voice apps that require STT/TTS chaining with a separate text model. Use OpenAI gpt-audio for direct speech-to-speech interactions and non-latency-sensitive tasks like batch transcription or audiobook narration.

Related Skills

Explore More Software Engineering Skills→
parisgroup-aiparisgroup-ai
1

db-migration

Generate, inspect, and apply Drizzle ORM migrations in Docker-based monorepos.

Official
Advanced
SstoboSstobo
25

Convex Agents Usage Tracking

Log LLM token usage and billing data for Convex Agents.

Community
Advanced
zzafergokzzafergok
1

voice-ai-development

Orchestrate real-time voice AI workflows across OpenAI Realtime, Vapi, Deepgram, ElevenLabs, and LiveKit.

Community
Advanced
PsychQuantPsychQuant

openai-docs-guide

Retrieve OpenAI API documentation for endpoints, models, pricing, and SDKs.

Official
Intermediate