Overview

import TTSKit

Task {
    let tts = try await TTSKit()
    let result = try await tts.generate(text: "Hello from TTSKit!")
    print("Generated \(result.audioDuration)s of audio at \(result.sampleRate)Hz")
}

// Fast, runs on all platforms
let tts = try await TTSKit(TTSKitConfig(model: .qwen3TTS_0_6b))

// Higher quality, macOS only
let tts = try await TTSKit(TTSKitConfig(model: .qwen3TTS_1_7b))

public class TTSKit {
    // Model components (protocol-typed, swappable)
    public var textProjector: any TextProjecting
    public var codeEmbedder: any CodeEmbedding
    public var multiCodeEmbedder: any MultiCodeEmbedding
    public var codeDecoder: any CodeDecoding
    public var multiCodeDecoder: any MultiCodeDecoding
    public var speechDecoder: any SpeechDecoding
    public var tokenizer: (any Tokenizer)?
}

let config = TTSKitConfig(load: false)
let tts = try await TTSKit(config)
tts.codeDecoder = MyOptimizedCodeDecoder()
try await tts.loadModels()

// Auto-load on init (default)
let tts = try await TTSKit()

// Manual control
let config = TTSKitConfig(load: false)
let tts = try await TTSKit(config)

// Prewarm: compile models sequentially to cap peak memory
try await tts.prewarmModels()

// Load: load all models concurrently
try await tts.loadModels()

// Unload to free memory
await tts.unloadModels()

public enum ModelState {
    case unloaded
    case downloading
    case downloaded
    case loading
    case loaded
    case prewarming
    case prewarmed
    case unloading
}