> ## Documentation Index > Fetch the complete documentation index at: https://mintlify.com/argmaxinc/WhisperKit/llms.txt > Use this file to discover all available pages before exploring further. # Model Catalog > Available Whisper and TTS models for WhisperKit and TTSKit ## WhisperKit Models All WhisperKit models are hosted on [HuggingFace](https://huggingface.co/argmaxinc/whisperkit-coreml) in CoreML format, optimized for Apple Neural Engine. ### Model Repository Browse all available models on HuggingFace ## Standard Whisper Models ### Tiny **Model ID**: `openai_whisper-tiny` \~40 MB 39M \~200 MB RAM 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:** ```swift theme={null} let pipe = try await WhisperKit(WhisperKitConfig(model: "tiny")) ``` ### Base **Model ID**: `openai_whisper-base` \~75 MB 74M \~300 MB RAM 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:** ```swift theme={null} let pipe = try await WhisperKit(WhisperKitConfig(model: "base")) ``` ### Small **Model ID**: `openai_whisper-small` \~250 MB 244M \~800 MB RAM 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:** ```swift theme={null} let pipe = try await WhisperKit(WhisperKitConfig(model: "small")) ``` ### Medium **Model ID**: `openai_whisper-medium` \~800 MB 769M \~2 GB RAM 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:** ```swift theme={null} let pipe = try await WhisperKit(WhisperKitConfig(model: "medium")) ``` ### Large V3 **Model ID**: `openai_whisper-large-v3` \~1.6 GB 1.55B \~4 GB RAM 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:** ```swift theme={null} 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` \~800 MB 756M 50% smaller, 2x faster \~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:** ```swift theme={null} 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 ### 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 | ### 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 ### 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](https://github.com/argmaxinc/whisperkittools). ### Creating Custom Models Use whisperkittools to fine-tune on your dataset: ```bash theme={null} python -m whisperkittools.train \ --model large-v3 \ --dataset your_dataset \ --output-dir custom_model ``` Convert the fine-tuned model to CoreML: ```bash theme={null} python -m whisperkittools.convert \ --model custom_model \ --output-dir coreml_model ``` Upload to your HuggingFace repository: ```bash theme={null} huggingface-cli upload username/model-repo coreml_model ``` Load your custom model: ```swift theme={null} 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 ### Qwen3 TTS 0.6B **Model ID**: `qwen3TTS_0_6b` \~1 GB 600M macOS, iOS 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:** ```swift theme={null} let tts = try await TTSKit(TTSKitConfig(model: .qwen3TTS_0_6b)) let result = try await tts.generate(text: "Hello!") ``` ### Qwen3 TTS 1.7B **Model ID**: `qwen3TTS_1_7b` \~2.2 GB 1.7B macOS only 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:** ```swift theme={null} 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: ```swift theme={null} // Downloads default model for device let pipe = try await WhisperKit() ``` ### Manual Download Download specific models via CLI: ```bash theme={null} # 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: ```bash theme={null} rm -rf ~/.cache/whisperkit/ ``` ## Performance Benchmarks Compare performance across devices and models ## Next Steps Check device compatibility Run performance tests Start transcribing Create fine-tuned models