MacPaw/OpenAI

Swift community driven package for OpenAI public API

What it solves

This project provides a community-maintained Swift SDK for interacting with the OpenAI API. It simplifies the process of integrating AI capabilities—such as text generation, image creation, audio processing, and assistant management—into Swift-based applications (iOS, macOS, etc.) without needing to manually handle complex REST API requests.

How it works

The library acts as a wrapper around OpenAI's REST API. Developers initialize the client with an API token and then use Swift-native methods to send queries and receive strongly-typed responses. It supports modern Swift features like Swift Concurrency (async/await) for clean, readable code, as well as Combine for reactive programming. It also supports OpenAI-compatible APIs from other providers.

Who it’s for

This is for Swift and Apple platform developers who want to build AI-powered features into their applications. It is designed for those who prefer using a native library over writing raw network requests to interact with LLMs and generative AI services.

Highlights

  • Comprehensive API Coverage: Includes support for Chat Completions, DALL-E image generation, audio transcription/translation, and Assistants API.
  • Modern Swift Support: Fully compatible with Swift Concurrency (async/await) and Combine.
  • Flexible Integration: Can be used with OpenAI or other providers that offer OpenAI-compatible endpoints.
  • Type-Safe: Uses Swift structures to model API requests and responses, reducing errors compared to handling raw JSON.

Related

  • Project
    jamesrochabrun/SwiftOpenAI

    SwiftOpenAI is a Swift package that wraps every OpenAI endpoint—including chat, audio (transcription, speech, realtime voice), images, embeddings, fine‑tuning, and the Assistants API—providing async/await, streaming, and support for Azure/other compatible providers on iOS, macOS, watchOS, and Linux.

  • Project
    openai/openai-java

    Official Java client library for OpenAI’s REST API, offering sync/async, streaming, workload‑identity auth, and optional Bedrock support.

  • Project
    sashabaranov/go-openai

    go‑openai is an unofficial Go client library that wraps the OpenAI API (text, chat, embeddings, images, audio, fine‑tuning, etc.). It supports the new Responses API for tool‑calling and multi‑turn state, provides model constants, Azure compatibility, streaming, and typed error handling, and includes runnable examples.

  • Project
    AIProxyTeam/AIProxySwift

    A Swift library for integrating various AI APIs into apps with an optional secure proxy backend to protect API keys and manage rate limits.

  • Project
    soniqo/speech-swift

    Speech Swift is an open‑source Swift package that provides on‑device speech AI for Apple Silicon. It bundles many modern ASR, TTS, translation, and voice‑agent models (e.g., Qwen3‑ASR, Whisper‑ASR, Omnilingual ASR, Qwen3‑TTS, CosyVoice, PersonaPlex) built on MLX and Core ML, so you can run inference locally with no cloud calls. Each model is a separate Swift‑Package‑Manager product, making it easy to add only what you need. The repo includes quick‑start code, SwiftUI UI helpers, Homebrew install, and extensive documentation.