Model Catalog

Available Whisper and TTS models for WhisperKit and TTSKit

WhisperKit Models

All WhisperKit models are hosted on HuggingFace in CoreML format, optimized for Apple Neural Engine.

Model Repository

WhisperKit CoreML Models

Browse all available models on HuggingFace

Standard Whisper Models

tiny

Tiny

Model ID: openai_whisper-tiny

Size

~40 MB

Parameters

39M

Memory

~200 MB RAM

Speed

Fastest

Best for:

• Quick testing and prototyping
• Resource-constrained devices
• When speed is more important than accuracy
• iPhone 13 and earlier devices

Performance:

• Real-time on all supported devices
• WER (Word Error Rate): ~15-20% on English
• RTF < 0.2 on most devices

Usage:

let pipe = try await WhisperKit(WhisperKitConfig(model: "tiny"))

base

Base

Model ID: openai_whisper-base

Size

~75 MB

Parameters

74M

Memory

~300 MB RAM

Speed

Very Fast

Best for:

• Balance of speed and accuracy
• General-purpose transcription
• iPhone 13 and newer
• Apps requiring low latency

Performance:

• Real-time on all supported devices
• WER: ~10-15% on English
• RTF < 0.3 on most devices

Usage:

let pipe = try await WhisperKit(WhisperKitConfig(model: "base"))

small

Small

Model ID: openai_whisper-small

Size

~250 MB

Parameters

244M

Memory

~800 MB RAM

Speed

Fast

Best for:

• Good accuracy with reasonable speed
• iPhone 14 and newer
• M1 Macs and above
• Production applications

Performance:

• Real-time on iPhone 14 Pro and newer
• WER: ~8-12% on English
• RTF ~0.4-0.6 on modern devices

Usage:

let pipe = try await WhisperKit(WhisperKitConfig(model: "small"))

medium

Medium

Model ID: openai_whisper-medium

Size

~800 MB

Parameters

769M

Memory

~2 GB RAM

Speed

Moderate

Best for:

• High accuracy requirements
• iPhone 15 Pro and newer
• M1 Macs and above
• Offline transcription tasks

Performance:

• Real-time on iPhone 15 Pro, M1 Mac+
• WER: ~6-9% on English
• RTF ~0.7-1.0 on modern devices

Usage:

let pipe = try await WhisperKit(WhisperKitConfig(model: "medium"))

large-v3

Large V3

Model ID: openai_whisper-large-v3

Size

~1.6 GB

Parameters

1.55B

Memory

~4 GB RAM

Speed

Slower

Best for:

• Maximum accuracy
• Desktop/server applications
• Mac Studio, MacBook Pro (M3 Pro+)
• Offline high-quality transcription

Performance:

• Real-time on M2 Pro and above
• WER: ~4-6% on English
• RTF ~1.2-2.0 depending on device
• Best multilingual support

Usage:

let pipe = try await WhisperKit(WhisperKitConfig(model: "large-v3"))

Distilled Models

Distilled models provide significant performance improvements with minimal accuracy loss through knowledge distillation.

Distil-Large-V3

Model ID: distil-whisper_distil-large-v3

Size

~800 MB

Parameters

756M

vs. Large-V3

50% smaller, 2x faster

Accuracy

~95% of large-v3

Advantages:

• Significantly faster than large-v3
• Much smaller download and memory footprint
• Near-identical accuracy to large-v3
• Real-time on iPhone 15 Pro
• Recommended for most use cases

Performance:

• WER: ~5-7% on English
• RTF ~0.6-0.9 on modern devices
• Runs well on iPhone 14 Pro and newer

Usage:

let pipe = try await WhisperKit(WhisperKitConfig(model: "distil*large-v3"))
// Glob pattern matches distil-whisper_distil-large-v3

Other Distilled Models

Several other distilled variants are available in the model repository:

• distil-whisper_distil-medium.en
• distil-whisper_distil-small.en

These are English-only models optimized for even faster inference.

Model Selection Guide

By Device

iPhone

Device	Recommended	Real-Time
iPhone 15 Pro	distil-large-v3, medium	large-v3
iPhone 14 Pro	medium, small	medium
iPhone 13 Pro	small, base	small
iPhone 12/13	base, tiny	base

iPad

Device	Recommended	Real-Time
iPad Pro (M1+)	large-v3, distil-large-v3	large-v3
iPad Air (M1+)	medium, distil-large-v3	medium
iPad (A14+)	small, base	small

Mac

Device	Recommended	Real-Time
Mac Studio (Ultra)	large-v3	All models
MacBook Pro (M3 Pro+)	large-v3	large-v3
MacBook Air (M1+)	distil-large-v3, medium	medium
Mac mini (M1+)	medium, small	small

By Use Case

Real-Time Streaming

• Best: tiny, base, small
• Good: medium (on powerful devices)
• Use: distil-large-v3 for best accuracy/speed balance

Offline Transcription

• Best: large-v3, distil-large-v3
• Good: medium
• When speed matters: small, base

Multilingual

• Best: large-v3 (supports 99+ languages)
• Good: medium (good multilingual support)
• Acceptable: small (limited multilingual)
• Not recommended: tiny, base (poor multilingual)

Low-Resource Devices

• Best: tiny, base
• Alternative: distil-small.en (English only)
• Consider: Server-based transcription for accuracy

High Accuracy

• Best: large-v3
• Nearly as good: distil-large-v3 (much faster)
• Good: medium

By Language

English Only

• Best accuracy: large-v3, distil-large-v3
• Best speed: distil-small.en, distil-medium.en
• Balanced: small, medium

Multilingual (99+ languages)

All standard models support multiple languages:

• Best: large-v3
• Good: medium
• Acceptable: small
• Limited: base, tiny

Specific Language Performance

Large models perform better on:

• Chinese (Mandarin, Cantonese)
• Japanese
• Arabic
• Korean
• Indian languages

Small models are sufficient for:

• Spanish
• French
• German
• Italian
• Portuguese

Custom Models

You can create and deploy custom fine-tuned models using whisperkittools.

Creating Custom Models

1. Fine-tune Whisper

   Use whisperkittools to fine-tune on your dataset:

   python -m whisperkittools.train \
     --model large-v3 \
     --dataset your_dataset \
     --output-dir custom_model
   
2. Convert to CoreML

   Convert the fine-tuned model to CoreML:

   python -m whisperkittools.convert \
     --model custom_model \
     --output-dir coreml_model
   
3. Upload to HuggingFace

   Upload to your HuggingFace repository:

   huggingface-cli upload username/model-repo coreml_model
   
4. Use in WhisperKit

   Load your custom model:

   let config = WhisperKitConfig(
       model: "large-v3",
       modelRepo: "username/model-repo"
   )
   let pipe = try await WhisperKit(config)
   

Use Cases for Custom Models

• Domain-specific vocabulary (medical, legal, technical)
• Accents and dialects
• Background noise handling
• Custom wake words
• Language variants

TTSKit Models

0.6B

Qwen3 TTS 0.6B

Model ID: qwen3TTS_0_6b

Size

~1 GB

Parameters

600M

Platforms

macOS, iOS

Speed

Fast

Features:

• 9 voices
• 10 languages
• Real-time streaming
• Runs on all platforms

Performance:

• Generates ~2-3s audio per second on M1
• Suitable for real-time playback
• Lower memory requirements

Usage:

let tts = try await TTSKit(TTSKitConfig(model: .qwen3TTS_0_6b))
let result = try await tts.generate(text: "Hello!")

1.7B

Qwen3 TTS 1.7B

Model ID: qwen3TTS_1_7b

Size

~2.2 GB

Parameters

1.7B

Platforms

macOS only

Quality

Higher

Features:

• 9 voices (same as 0.6B)
• 10 languages
• Style instructions (unique to 1.7B)
• Better prosody and naturalness

Performance:

• Generates ~1-2s audio per second on M1
• Requires more memory (~4 GB)
• macOS 15.0+ required

Usage:

let tts = try await TTSKit(TTSKitConfig(model: .qwen3TTS_1_7b))

var options = GenerationOptions()
options.instruction = "Speak warmly and slowly."

let result = try await tts.generate(
    text: "Hello!",
    options: options
)

TTSKit Voices

All models support these 9 voices:

Voice	Style	Best For
.ryan	Clear, professional	Business, narration
.aiden	Warm, friendly	Customer service
.onoAnna	Bright, energetic	Announcements
.sohee	Calm, soothing	Meditation, audiobooks
.eric	Deep, authoritative	News, presentations
.dylan	Young, casual	Social media, gaming
.serena	Elegant, refined	Luxury brands
.vivian	Confident, dynamic	Fitness, motivation
.uncleFu	Wise, mature	Storytelling, teaching

TTSKit Languages

• English
• Chinese (Mandarin)
• Japanese
• Korean
• German
• French
• Russian
• Portuguese
• Spanish
• Italian

Model Download

Automatic Download

WhisperKit automatically downloads the recommended model on first use:

// Downloads default model for device
let pipe = try await WhisperKit()

Manual Download

Download specific models via CLI:

# Download single model
make download-model MODEL=large-v3

# Download all models
make download-models

Model Caching

Models are cached at:

• macOS: ~/.cache/whisperkit/
• iOS: App’s cache directory

To clear cache:

rm -rf ~/.cache/whisperkit/

Performance Benchmarks

View Detailed Benchmarks

Compare performance across devices and models

Next Steps

Supported Devices

Check device compatibility

Benchmarks

Run performance tests

Quick Start

Start transcribing

Custom Models

Create fine-tuned models