diff --git a/web/src/components/Toolbar.tsx b/web/src/components/Toolbar.tsx
index 5bda6e9..2f431a5 100644
--- a/web/src/components/Toolbar.tsx
+++ b/web/src/components/Toolbar.tsx
@@ -3,6 +3,7 @@ import { useInputBarStore } from '../store/inputBar';
 import { useGenerationStore } from '../store/generation';
 import { useAuthStore } from '../store/auth';
 import { Dropdown } from './Dropdown';
+import { showToast } from './Toast';
 import type { CreationMode, AspectRatio, Duration, GenerationType, ModelOption } from '../types';
 import styles from './Toolbar.module.css';
 
@@ -145,7 +146,14 @@ export function Toolbar() {
   }, [estimatedTokens, model, references, team]);
 
   const handleSend = useCallback(() => {
-    if (!isSubmittable) return;
+    if (!isSubmittable) {
+      const s = useInputBarStore.getState();
+      if (s.mode === 'universal' && s.references.some((r) => r.type === 'audio')
+        && !s.references.some((r) => r.type === 'image' || r.type === 'video')) {
+        showToast('音频不能作为唯一的参考素材，请同时添加图片或视频');
+      }
+      return;
+    }
     addTask();
   }, [isSubmittable, addTask]);
 
diff --git a/web/src/store/inputBar.ts b/web/src/store/inputBar.ts
index dc3900d..b434f51 100644
--- a/web/src/store/inputBar.ts
+++ b/web/src/store/inputBar.ts
@@ -285,10 +285,19 @@ export const useInputBarStore = create<InputBarState>((set, get) => ({
         ? state.references.length > 0
         : state.firstFrame !== null || state.lastFrame !== null;
     if (!hasText && !hasFiles) return false;
-    // Audio cannot be sent alone — must have image or video
-    if (state.mode === 'universal' && state.references.length > 0) {
-      const hasImageOrVideo = state.references.some((r) => r.type === 'image' || r.type === 'video');
-      if (!hasImageOrVideo && !hasText) return false;
+    // Audio cannot be the only reference — Seedance API requires image or video alongside
+    if (state.mode === 'universal') {
+      const hasAudioRef = state.references.some((r) => r.type === 'audio');
+      const hasAudioAsset = (state.assetMentions || []).some((m: Record<string, string>) =>
+        (m.assetType || '').toLowerCase() === 'audio');
+      if (hasAudioRef || hasAudioAsset) {
+        const hasImageOrVideoRef = state.references.some((r) => r.type === 'image' || r.type === 'video');
+        const hasImageOrVideoAsset = (state.assetMentions || []).some((m: Record<string, string>) => {
+          const t = (m.assetType || '').toLowerCase();
+          return t === 'image' || t === 'video';
+        });
+        if (!hasImageOrVideoRef && !hasImageOrVideoAsset) return false;
+      }
     }
     // Block submit if any reference is still uploading or failed
     if (state.references.some((r) => r.uploading || r.uploadError)) return false;