Supertonic 2

ios/ExampleiOSApp/ContentView.swift

@@ -12,7 +12,7 @@ struct ContentView: View {
                 Spacer()
 
                 VStack(spacing: 12) {
-                    Text("SupertonicTTS iOS Demo")
+                    Text("Supertonic 2 iOS Demo")
                         .font(.title2.weight(.semibold))
                         .foregroundColor(.primary)
 
@@ -44,6 +44,19 @@ struct ContentView: View {
                     }
                     .pickerStyle(SegmentedPickerStyle())
                     .padding(.horizontal)
+                    
+                    HStack(spacing: 12) {
+                        Text("Language")
+                            .font(.subheadline)
+                            .foregroundColor(.secondary)
+                        Picker("Language", selection: $vm.language) {
+                            ForEach(TTSService.Language.allCases, id: \.self) { lang in
+                                Text(lang.displayName).tag(lang)
+                            }
+                        }
+                        .pickerStyle(MenuPickerStyle())
+                    }
+                    .padding(.horizontal)
                 }
 
                 HStack(spacing: 16) {

ios/ExampleiOSApp/TTSService.swift

@@ -3,6 +3,23 @@ import OnnxRuntimeBindings
 
 final class TTSService {
     enum Voice { case male, female }
+    enum Language: String, CaseIterable {
+        case en = "en"
+        case ko = "ko"
+        case es = "es"
+        case pt = "pt"
+        case fr = "fr"
+        
+        var displayName: String {
+            switch self {
+            case .en: return "English"
+            case .ko: return "한국어"
+            case .es: return "Español"
+            case .pt: return "Português"
+            case .fr: return "Français"
+            }
+        }
+    }
 
     private let env: ORTEnv
     private let textToSpeech: TextToSpeech
@@ -16,13 +33,13 @@ final class TTSService {
         sampleRate = textToSpeech.sampleRate
     }
 
-    func synthesize(text: String, nfe: Int, voice: Voice) async throws -> URL {
+    func synthesize(text: String, nfe: Int, voice: Voice, language: Language) async throws -> URL {
         // Load style for the selected voice
         let styleURL = try Self.locateVoiceStyleURL(voice: voice)
         let style = try loadVoiceStyle([styleURL.path], verbose: false)
 
         // 2) Synthesize via packed TextToSpeech component
-        let (wav, duration) = try textToSpeech.call(text, style, nfe)
+        let (wav, duration) = try textToSpeech.call(text, language.rawValue, style, nfe)
         let audioSeconds = Double(duration)
         let wavLenSample = min(Int(Double(sampleRate) * audioSeconds), wav.count)
         let wavOut = Array(wav[0..<wavLenSample])

ios/ExampleiOSApp/TTSViewModel.swift

@@ -6,6 +6,7 @@ final class TTSViewModel: ObservableObject {
     @Published var text: String = "This morning, I took a walk in the park, and the sound of the birds and the breeze was so pleasant that I stopped for a long time just to listen."
     @Published var nfe: Double = 5
     @Published var voice: TTSService.Voice = .male
+    @Published var language: TTSService.Language = .en
     @Published var isGenerating: Bool = false
     @Published var isPlaying: Bool = false
     @Published var errorMessage: String?
@@ -39,7 +40,7 @@ final class TTSViewModel: ObservableObject {
         Task {
             let tic = Date()
             do {
-                let url = try await service.synthesize(text: text, nfe: Int(nfe), voice: voice)
+                let url = try await service.synthesize(text: text, nfe: Int(nfe), voice: voice, language: language)
                 let elapsed = Date().timeIntervalSince(tic)
                 let audio = audioDuration(at: url)
                 await MainActor.run {

ios/README.md

@@ -1,9 +1,10 @@
 # Supertonic iOS Example App
 
-A minimal iOS demo that runs Supertonic (ONNX Runtime) on-device. The app shows:
+A minimal iOS demo that runs Supertonic 2 (ONNX Runtime) on-device. The app shows:
 - Multiline text input
 - NFE (denoising steps) slider
 - Voice toggle (M/F)
+- Language selector (en, ko, es, pt, fr)
 - Generate & Play buttons
 - RTF display (Elapsed / Audio seconds)
 
@@ -11,6 +12,8 @@ All ONNX models/configs are reused from `Supertonic/assets/onnx`, and voice styl
 
 ## 📰 Update News
 
+**2026.01.06** - 🎉 **Supertonic 2** released with multilingual support! Now supports English (`en`), Korean (`ko`), Spanish (`es`), Portuguese (`pt`), and French (`fr`). [Demo](https://huggingface.co/spaces/Supertone/supertonic-2) | [Models](https://huggingface.co/Supertone/supertonic-2)
+
 **2025.12.10** - Added [6 new voice styles](https://huggingface.co/Supertone/supertonic/tree/b10dbaf18b316159be75b34d24f740008fddd381) (M3, M4, M5, F3, F4, F5). See [Voices](https://supertone-inc.github.io/supertonic-py/voices/) for details
 
 **2025.12.08** - Optimized ONNX models via [OnnxSlim](https://github.com/inisis/OnnxSlim) now available on [Hugging Face Models](https://huggingface.co/Supertone/supertonic)
@@ -59,7 +62,17 @@ These references are defined in `project.yml` and added to the app bundle by Xco
 ## App Controls
 - **Text**: Multiline `TextEditor`
 - **NFE**: Denoising steps (default 5)
-- **Voice**: M1/M2/F1/F2 voice style selector (4 pre-extracted styles)
+- **Voice**: M/F voice style selector
+- **Language**: Language selector (English, 한국어, Español, Português, Français)
 - **Generate**: Runs end-to-end synthesis
 - **Play/Stop**: Controls playback of the last output
-- **RTF**: Shows Elapsed / Audio seconds for quick performance intuition
+- **RTF**: Shows Elapsed / Audio seconds for quick performance intuition
+
+## Multilingual Support
+
+Supertonic 2 supports multiple languages. Select the appropriate language for your input text:
+- **English (en)**: Default language
+- **한국어 (ko)**: Korean
+- **Español (es)**: Spanish
+- **Português (pt)**: Portuguese
+- **Français (fr)**: French