diff --git a/studio/frontend/src/features/training/api/models-api.ts b/studio/frontend/src/features/training/api/models-api.ts
index 79560975f5..2ed4645b16 100644
--- a/studio/frontend/src/features/training/api/models-api.ts
+++ b/studio/frontend/src/features/training/api/models-api.ts
@@ -62,6 +62,7 @@ export interface ModelConfigResponse {
   config?: BackendModelConfig | null;
   is_vision: boolean;
   is_lora: boolean;
+  is_audio?: boolean;
   base_model?: string | null;
   model_type?: "text" | "vision" | "tts" | "embeddings" | null;
 }
diff --git a/studio/frontend/src/features/training/stores/training-config-store.ts b/studio/frontend/src/features/training/stores/training-config-store.ts
index c414ea0963..1ae404cb61 100644
--- a/studio/frontend/src/features/training/stores/training-config-store.ts
+++ b/studio/frontend/src/features/training/stores/training-config-store.ts
@@ -130,7 +130,7 @@ export const useTrainingConfigStore = create<TrainingConfigStore>()(
             // Use backend-provided model_type when available, otherwise
             // infer from is_vision (temporary until backend ships model_type).
             const inferredModelType: ModelType = modelDetails.model_type
-              ?? (modelDetails.is_vision ? "vision" : "text");
+              ?? (modelDetails.is_vision ? "vision" : modelDetails.is_audio ? "tts" : "text");
 
             set({
               ...patch,