Overview
What the Rapidly SDK is, where it runs, and how it's distributed.
Rapidly is a real-time audio separation SDK. The engine runs entirely on the end-user's device across Linux, Windows, macOS, iOS, and Android, with idiomatic bindings for C / C++, Python, Swift, and Kotlin. Inference latency starts at 11 ms.
Vocabulary
Three terms used across these docs.
For when you need more than one engine, see One vs multiple engines and Parallel processing.
Key strengths
On-device inference
Audio never leaves the device. The full engine runs locally, with no cloud round-trip for inference.
Real-time, low latency
Latency from 11 ms to 96 ms across the model catalog. Real-time factor up to 125x on a single CPU core.
Five platforms
Linux, Windows, macOS, iOS, and Android. The same engine runs everywhere.
Four language bindings
C / C++, Python, Swift, and Kotlin. Distributed via the standard package manager for each language.
Hardware-accelerated math
Apple Accelerate (vDSP), Intel IPP, and ARM NEON paths selected automatically per platform.
Small footprint
Compact models from 241 KB. Suits CPU-constrained embedded and mobile targets.
Pick your binding
C / C++
The most direct path. Desktop, server, embedded, or any native integration.
Python
Servers, ML pipelines, and notebooks.
Swift
iOS and macOS apps via Swift Package Manager.
Kotlin
Android apps via Maven Central.
Supported platforms
| Platform | Architectures | Distribution |
|---|---|---|
| Linux | x64, arm64 | Shared library in bin/linux-x64/ and bin/linux-arm64/ |
| Windows | x64, x86 | DLL plus import library in bin/windows-x64/ and bin/windows-x86/ |
| macOS | Universal (arm64 + x86_64) | dylib in bin/macos/, or the signed RapidlyEngine.xcframework, or Swift Package Manager |
| iOS | arm64 device and Simulator | RapidlyEngine.xcframework, or Swift Package Manager |
| Android | arm64-v8a | Maven Central (io.rapidly:rapidly-sdk:1.0), or .aar from the GitHub Release |
Minimum requirements
- iOS 14 or later, iPadOS 14 or later
- macOS 11 or later
- Android
minSdk26 (Android 8.0)
Linux and Windows do not have a hard minimum; any reasonably modern distribution or release should work.
What the SDK includes
| Component | Purpose |
|---|---|
| Native engine binary | The cross-platform core that loads models and runs inference. One binary per platform. |
Public C header (RapidlyEngine.h) | The stable API surface that every binding wraps. |
| Language bindings | Idiomatic wrappers for C / C++, Python, Swift, and Kotlin. |
| Pre-trained models | .rapidly files for speech denoising and dereverberation, in multiple latency variants. See Models. |
| Examples | Working integrations for file processing and embedded targets, shipped in the GitHub Release. |
Distribution
The SDK ships as a GitHub Release with pre-built binaries, the Apple xcframework, the Android .aar, the public header, and the bindings source. Customers can also pull bindings directly from each language's package manager:
| Channel | What's there |
|---|---|
| GitHub Release | Pre-built binaries, the xcframework, the .aar, the public header, and the bindings source. |
| PyPI | pip install rapidly for the Python binding. |
| Swift Package Manager | https://github.com/rapidly-labs/rapidly-sdk for the Swift binding. |
| Maven Central | io.rapidly:rapidly-sdk:1.0 for the Kotlin binding. |
Hardware acceleration
The engine selects the fastest available math path per platform at runtime:
| Platform | Acceleration |
|---|---|
| Apple (macOS, iOS) | Accelerate framework (vDSP) |
| Intel desktop and server | Intel Performance Primitives (IPP) |
| ARM (Linux arm64, Android, Apple Silicon) | NEON intrinsics |
| Other targets | Optimised C++ fallback |
No configuration is required. The engine picks the best path per architecture on its own.
Coming soon
WebAssembly. WASM is on the roadmap to enable in-browser audio processing without a server round-trip. Target use cases: web apps, SaaS products, browser-based conferencing, live streaming, and smart TVs running web-based platforms like Samsung Tizen or LG webOS.
NPU offload. Hardware-accelerated inference on chips with dedicated neural acceleration units.
Licensing model
The SDK enforces license entitlements locally. No network access is required. Without a covering license, the engine still runs and loads models, but its output is watermarked. See Pricing for licensing options.