MacPaw/OpenAI

Swift community driven package for OpenAI public API

What it solves

This project provides a community-maintained Swift implementation of the OpenAI public API, allowing Apple developers to integrate AI capabilities into their apps without writing raw REST API requests.

How it works

It acts as a Swift SDK wrapper around the OpenAI REST API. It defines types and methods that closely match the official API documentation, supporting various request patterns including Swift Concurrency (async/await), closure-based calls, and Combine subscriptions. While optimized for OpenAI, it can also work with other OpenAI-compatible providers (such as Gemini, DeepSeek, and Perplexity) by using a relaxed parsing configuration.

Who it’s for

iOS, macOS, and other Apple platform developers who want to integrate LLMs, image generation, and audio processing into their Swift applications.

Highlights

  • Comprehensive API Coverage: Supports chat completions, text responses, image generation/editing/variation, audio transcriptions/translations, and embeddings.
  • Advanced AI Features: Includes support for function calling, structured outputs, and the Assistants API (Beta).
  • **Model Context Protocol (MCP): Integration for MCP tools.
  • Flexible Integration: Compatible with Swift Package Manager and supports multiple asynchronous programming patterns.

Related

  • Project
    jamesrochabrun/SwiftOpenAI

    A Swift package for effortless interaction with OpenAI's API and other OpenAI-compatible providers, supporting text, image, audio, and real-time voice conversations.

  • Project
    scouzi1966/maclocal-api

    A native Swift AI infrastructure for Apple Silicon that turns a Mac into a private, OpenAI-compatible AI server supporting MLX and Apple Foundation Models.

  • Project
    Blaizzy/mlx-audio-swift

    A modular Swift SDK for audio processing on Apple Silicon, providing on-device support for text-to-speech, speech-to-text, and speaker diarization using the MLX framework.

  • Project
    cubist38/mlx-openai-server

    An OpenAI-compatible API server for running local MLX models on Apple Silicon, supporting text, multimodal, image, and audio models.

  • Project
    FluidInference/FluidAudio

    A Swift SDK for local, low-latency audio AI on Apple devices, providing transcription, text-to-speech, and speaker diarization offloaded to the Apple Neural Engine.