Last updated: March 24, 2025

<span aria-hidden="true" id="transcribe-audio-on-ios--macos-whisperkit"></span>

# Transcribe audio on iOS & macOS: Whisperkit

![Kevin van Zonneveld](/assets/images/teammates/avatar-kvz-4.jpg?dpl=dpl_C6YH6XrtnwbHLJcm1LDKywQn4CB3)

#### Kevin van Zonneveld

Co-founder · Amsterdam, The Netherlands · Show bio

[](https://x.com/kvz)[](https://github.com/kvz)

WhisperKit is an Apple-optimized implementation of OpenAI's Whisper speech recognition model, designed specifically for iOS and macOS applications. It provides efficient, on-device speech transcription capabilities with impressive accuracy, making it ideal for developers looking to add audio-to-text features to their apps.

<span aria-hidden="true" id="introduction-to-whisperkit-and-its-capabilities"></span>

## Introduction to Whisperkit and its capabilities

WhisperKit leverages Core ML to run Whisper models natively on Apple Silicon, providing robust transcription capabilities across multiple languages. It supports various audio formats and can handle challenging audio environments, making it suitable for diverse applications without requiring cloud connectivity.

<span aria-hidden="true" id="setting-up-whisperkit-on-ios-and-macos"></span>

## Setting up Whisperkit on iOS and macOS

To integrate WhisperKit into your apps, you'll need to set up the proper environment:

<span aria-hidden="true" id="prerequisites"></span>

### Prerequisites

* macOS 14.0 or later
* Xcode 15.0 or later
* Apple Silicon Mac for development (Intel Macs are not supported)
* iOS 15.0+ or macOS 13.0+ for deployment

<span aria-hidden="true" id="installation"></span>

### Installation

Add WhisperKit to your project using Swift Package Manager:

1. Open your Xcode project
2. Navigate to `File > Add Packages`
3. Enter the repository URL: `https://github.com/argmaxinc/WhisperKit.git`
4. Select the latest stable version (0.9.0 or newer) and add it to your project

Alternatively, add it directly to your `Package.swift` file:

```swift
dependencies: [
    .package(url: "https://github.com/argmaxinc/WhisperKit.git", from: "0.9.0"),
]

```

<span aria-hidden="true" id="step-by-step-guide-to-transcribing-audio-files"></span>

## Step-by-step guide to transcribing audio files

Here's how to implement audio transcription with WhisperKit in your Swift application:

```swift
import WhisperKit

// Basic transcription example
Task {
    do {
        // Initialize WhisperKit with default settings
        let pipe = try await WhisperKit()

        // Transcribe an audio file
        let audioPath = "path/to/your/audio.mp3" // Supports .wav, .mp3, .m4a, .flac
        let result = try await pipe.transcribe(audioPath: audioPath)

        // Access the transcribed text
        print("Transcription: \(result?.text ?? "No transcription available")")

    } catch {
        print("Error transcribing audio: \(error)")
    }
}

```

<span aria-hidden="true" id="using-a-specific-model"></span>

### Using a specific model

```swift
import WhisperKit

Task {
    do {
        // Configure WhisperKit with a specific model
        let config = WhisperKitConfig(model: "large-v3", modelRepo: "argmaxinc/whisperkit-coreml")
        let pipe = try await WhisperKit(config)

        // Transcribe audio
        let result = try await pipe.transcribe(audioPath: "recording.m4a")
        print(result?.text ?? "No transcription available")
    } catch {
        print("Error: \(error)")
    }
}

```

<span aria-hidden="true" id="optimizing-transcription-accuracy-and-performance"></span>

## Optimizing transcription accuracy and performance

To achieve optimal results with WhisperKit:

<span aria-hidden="true" id="audio-quality-considerations"></span>

### Audio quality considerations

* Use clear, high-quality audio recordings when possible.
* Minimize background noise in recording environments.
* For voice recordings, position microphones closer to speakers.

<span aria-hidden="true" id="model-selection"></span>

### Model selection

WhisperKit offers several model options with different size/performance tradeoffs:

* **tiny-en**: Smallest model, English only, fastest but least accurate.
* **base-en**: Small model, English only, a bit more accurate than `tiny-en`.
* **small-en**: Good accuracy with reasonable performance for English.
* **medium-en**: High accuracy with moderate performance impact for English.
* **large-v3**: Highest accuracy, but requires more memory and processing power. Supports multiple languages.

<span aria-hidden="true" id="performance-considerations"></span>

### Performance considerations

* Memory requirements vary significantly by model size (from \~30MB for `tiny-en` to \~1.5GB for`large-v3`).
* Processing time scales with model size and audio length.
* Apple Silicon devices (M1/M2/M3) provide significantly better performance than older devices.
* Consider using smaller models for real-time applications.

<span aria-hidden="true" id="practical-use-cases-and-examples"></span>

## Practical use cases and examples

WhisperKit can be effectively used in:

* Voice note applications with automatic transcription.
* Accessibility features for hearing-impaired users.
* Meeting and interview transcription tools.
* Podcast and video content transcription.
* Language learning applications.

<span aria-hidden="true" id="troubleshooting-common-issues"></span>

## Troubleshooting common issues

<span aria-hidden="true" id="model-download-failures"></span>

### Model download failures

**Issue**: Models fail to download or initialize.

**Solution**: Ensure proper internet connectivity and verify you have sufficient storage space. You can also pre-download models and include them in your app bundle:

```swift
let config = WhisperKitConfig(
    model: "large-v3",
    modelFolder: Bundle.main.resourceURL?.appendingPathComponent("Models").path
)

```

<span aria-hidden="true" id="memory-pressure"></span>

### Memory pressure

**Issue**: App crashes due to memory limitations.

**Solution**: Use a smaller model or implement transcription in smaller audio chunks:

```swift
// Process audio in 30-second segments
let audioChunks = splitAudioIntoChunks(audioPath: path, chunkDuration: 30)
var fullTranscription = ""

for chunk in audioChunks {
    let result = try await pipe.transcribe(audioPath: chunk)
    fullTranscription += result?.text ?? ""
}

```

<span aria-hidden="true" id="slow-transcription"></span>

### Slow transcription

**Issue**: Transcription takes too long for your use case.

**Solution**: Use a smaller model or adjust beam size in configuration:

```swift
var config = WhisperKitConfig(model: "small-en")
config.beamSize = 1  // Faster but potentially less accurate
let pipe = try await WhisperKit(config)

```

<span aria-hidden="true" id="streaming-transcription"></span>

## Streaming transcription

WhisperKit supports streaming audio for near real-time transcription. Here's how to use the CLI tool for streaming:

```bash
# For streaming audio directly from a microphone
swift run whisperkit-cli transcribe --model-path "Models/whisperkit-coreml/openai_whisper-large-v3" --stream

```

Refer to the WhisperKit documentation for implementing streaming transcription programmatically within your app.

<span aria-hidden="true" id="transloadits-speech-transcription-capabilities"></span>

## Transloadit's speech transcription capabilities

If you need a cloud-based solution without managing infrastructure, Transloadit offers a powerful speech transcription service as part of our[Artificial Intelligence service](/services/artificial-intelligence.md). Our 🤖[speech/transcribe Robot](/docs/robots/speech-transcribe.md) efficiently transcribes speech in audio or video files with these advantages:

* Support for multiple audio and video formats (MP3, WAV, MP4, MOV, etc.).
* Multiple provider options (AWS, GCP, Replicate, FAL, Transloadit).
* Various output formats (JSON, SRT, text, WebVTT).
* Support for over 100 languages.
* Automatic language detection.
* Speaker diarization options.

This cloud-based approach can be ideal for processing large files or when on-device processing isn't feasible.

Happy coding!

\#whisper#speech-transcription#ios#macos#open-source#audio-to-text#artificial-intelligence-service

### 👩‍💻 Join 20k+ developers

Sign up for our [monthly newsletter](/newsletters.md) to receive direct links to 3 exclusive tech — and 2 product updates. No less, no more.

Your email:

Get access

## File uploading and encoding. Made simple.

Transloadit streamlines file handling for developers, trusted by brands like Coursera and The New York Times. We’re known for a reliable API, top-notch support, and a strong commitment to open source, with projects like [Uppy⁠](https://uppy.io) and [Tus⁠](https://tus.io) setting standards in file processing.

[Sign up](/c/)[Book a Demo](https://survey.typeform.com/to/kRg47Xi5)

No credit card needed · 5 GB included in the free plan

Cancel anytime