Add voice preview and age category modifiers

Features: - Voice preview button to test voices before generation - Age category selection (young, teen, adult, old) - Age categories adjust voice speed automatically: - Young: 1.15x (faster, energetic) - Teen: 1.08x (slightly faster) - Adult: 1.0x (normal) - Old: 0.85x (slower, measured) - Preview caching to avoid regenerating same voice - Backend /api/tts/preview endpoint for voice samples - Frontend previewVoice API function This allows users to hear how each voice sounds and adjust character ages to make them sound younger or older.
2025-12-09 14:17:58 +00:00
parent a8636bcf71
commit 69eb0b3507
4 changed files with 298 additions and 22 deletions
--- a/backend/main.py
+++ b/backend/main.py
@@ -62,6 +62,13 @@ class TTSRequest(BaseModel):
    roles: List[RoleVoiceMapping] = Field(..., description="Role to voice mappings")
    speed: Optional[float] = Field(1.0, description="Playback speed (0.5-1.5)")

+class VoicePreviewRequest(BaseModel):
+    """Request model for voice preview endpoint."""
+    voice: str = Field(..., description="Kokoro voice ID to preview")
+    lang: str = Field(..., description="Language code (a, b, f, j)")
+    speed: Optional[float] = Field(1.0, description="Playback speed (0.5-1.5)")
+    text: Optional[str] = Field(None, description="Custom text to preview (uses default if not provided)")
+
 class ErrorResponse(BaseModel):
    """Standard error response model."""
    error: str = Field(..., description="Error type")
@@ -234,6 +241,90 @@ async def generate_script(request: ScriptRequest):
            }
        )

+@app.post("/api/tts/preview")
+async def preview_voice(request: VoicePreviewRequest):
+    """
+    Generates a short audio preview of a voice.
+    
+    Args:
+        request: VoicePreviewRequest containing voice ID, language, speed, and optional text
+        
+    Returns:
+        StreamingResponse with audio/wav content
+        
+    Raises:
+        400: If validation fails
+        500: If audio generation fails
+    """
+    logger.info(f"Voice preview requested: voice={request.voice}, lang={request.lang}, speed={request.speed}")
+    
+    # Validate language code
+    supported_langs = ['a', 'b', 'e', 'f', 'h', 'i', 'j', 'p', 'z']
+    if request.lang not in supported_langs:
+        logger.error(f"Invalid language code: {request.lang}")
+        return JSONResponse(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            content={
+                "error": "ValidationError",
+                "message": f"Invalid language code: {request.lang}",
+                "details": {"field": "lang", "supported": supported_langs}
+            }
+        )
+    
+    # Validate speed range
+    if request.speed < 0.5 or request.speed > 1.5:
+        logger.error(f"Invalid speed value: {request.speed}")
+        return JSONResponse(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            content={
+                "error": "ValidationError",
+                "message": "Speed must be between 0.5 and 1.5",
+                "details": {"field": "speed", "value": request.speed, "range": [0.5, 1.5]}
+            }
+        )
+    
+    # Use provided text or default preview text
+    preview_text = request.text or "Hello! This is a preview of this voice. How does it sound?"
+    
+    try:
+        # Get pipeline for language
+        pipeline = tts_service.get_pipeline(request.lang)
+        
+        # Generate preview audio
+        audio = tts_service.synthesize_segment(
+            pipeline=pipeline,
+            text=preview_text,
+            voice=request.voice,
+            speed=request.speed
+        )
+        
+        # Convert to WAV bytes
+        import io
+        import soundfile as sf
+        buffer = io.BytesIO()
+        sf.write(buffer, audio, tts_service.SAMPLE_RATE, format='WAV')
+        buffer.seek(0)
+        audio_bytes = buffer.read()
+        
+        logger.info(f"Generated voice preview: {len(audio_bytes)} bytes")
+        
+        return StreamingResponse(
+            iter([audio_bytes]),
+            media_type="audio/wav",
+            headers={"Content-Disposition": "inline; filename=preview.wav"}
+        )
+        
+    except Exception as e:
+        logger.error(f"Error during voice preview: {str(e)}", exc_info=True)
+        return JSONResponse(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            content={
+                "error": "PreviewGenerationError",
+                "message": "Failed to generate voice preview",
+                "details": {"error": str(e)}
+            }
+        )
+
@app.post("/api/tts")
 async def generate_audiobook(request: TTSRequest):
    """
--- a/frontend/src/App.tsx
+++ b/frontend/src/App.tsx
@@ -7,12 +7,15 @@ import AudioPlayerSection from './components/AudioPlayerSection'
 import type { Role, ScriptSegment } from './api/tts'
 import { detectRoles, generateScript, generateAudiobook } from './api/tts'

+type AgeCategory = 'young' | 'teen' | 'adult' | 'old';
+
 function App() {
  const [text, setText] = useState('')
  const [phase, setPhase] = useState<'input' | 'assignment' | 'review' | 'generated'>('input')
  const [isLoading, setIsLoading] = useState(false)
  const [roles, setRoles] = useState<Role[]>([])
  const [voiceAssignments, setVoiceAssignments] = useState<Map<string, string>>(new Map())
+  const [ageSettings, setAgeSettings] = useState<Map<string, AgeCategory>>(new Map())
  const [scriptSegments, setScriptSegments] = useState<ScriptSegment[]>([])
  const [language, setLanguage] = useState('a') // Default: American English
  const [speed, setSpeed] = useState(1.0) // Default: 1.0x
@@ -56,6 +59,14 @@ function App() {
    })
  }

+  const handleAgeChange = (roleId: string, age: AgeCategory) => {
+    setAgeSettings(prev => {
+      const newMap = new Map(prev)
+      newMap.set(roleId, age)
+      return newMap
+    })
+  }
+
  const handleLanguageChange = (lang: string) => {
    setLanguage(lang)
  }
@@ -281,7 +292,9 @@ function App() {
            <VoiceAssignmentSection
              roles={roles}
              voiceAssignments={voiceAssignments}
+              ageSettings={ageSettings}
              onVoiceChange={handleVoiceChange}
+              onAgeChange={handleAgeChange}
              language={language}
              onLanguageChange={handleLanguageChange}
              speed={speed}
--- a/frontend/src/api/tts.ts
+++ b/frontend/src/api/tts.ts
@@ -255,3 +255,35 @@ export async function generateAudiobook(payload: GenerateRequest): Promise<Blob>
  // Convert response to blob for audio data
  return await response.blob();
 }
+
+/**
+ * Request payload for voice preview
+ */
+export interface VoicePreviewRequest {
+  voice: string;
+  lang: string;
+  speed?: number;
+  text?: string;
+}
+
+/**
+ * Generate a preview of a voice
+ * @param payload - Preview request with voice, language, and optional speed/text
+ * @returns Promise resolving to audio blob
+ * @throws ApiError if the request fails
+ */
+export async function previewVoice(payload: VoicePreviewRequest): Promise<Blob> {
+  const baseUrl = getApiBaseUrl();
+  const url = `${baseUrl}/api/tts/preview`;
+  
+  const response = await fetchWithErrorHandling(url, {
+    method: 'POST',
+    headers: {
+      'Content-Type': 'application/json',
+    },
+    body: JSON.stringify(payload),
+  });
+  
+  // Convert response to blob for audio data
+  return await response.blob();
+}
--- a/frontend/src/components/VoiceAssignmentSection.tsx
+++ b/frontend/src/components/VoiceAssignmentSection.tsx
@@ -1,9 +1,15 @@
+import { useState } from 'react';
 import type { Role } from '../api/tts';
+import { previewVoice } from '../api/tts';
+
+type AgeCategory = 'young' | 'teen' | 'adult' | 'old';

 interface VoiceAssignmentSectionProps {
  roles: Role[];
  voiceAssignments: Map<string, string>;
+  ageSettings: Map<string, AgeCategory>;
  onVoiceChange: (roleId: string, voiceId: string) => void;
+  onAgeChange: (roleId: string, age: AgeCategory) => void;
  language: string;
  onLanguageChange: (lang: string) => void;
  speed: number;
@@ -130,10 +136,20 @@ const LANGUAGES: LanguageOption[] = [
  { code: 'z', label: 'Chinese (中文)' },
 ];

+// Age category to speed mapping
+const AGE_SPEED_MAP: Record<AgeCategory, number> = {
+  young: 1.15,
+  teen: 1.08,
+  adult: 1.0,
+  old: 0.85,
+};
+
 export default function VoiceAssignmentSection({
  roles,
  voiceAssignments,
+  ageSettings,
  onVoiceChange,
+  onAgeChange,
  language,
  onLanguageChange,
  speed,
@@ -143,8 +159,71 @@ export default function VoiceAssignmentSection({
  isGenerating,
  allRolesAssigned,
 }: VoiceAssignmentSectionProps) {
+  const [previewingRole, setPreviewingRole] = useState<string | null>(null);
+  const [audioCache, setAudioCache] = useState<Map<string, string>>(new Map());
+
  const handleVoiceSelect = (roleId: string, voiceId: string) => {
    onVoiceChange(roleId, voiceId);
+    // Clear cached preview when voice changes
+    const cacheKey = `${roleId}-${voiceId}`;
+    setAudioCache(prev => {
+      const newCache = new Map(prev);
+      newCache.delete(cacheKey);
+      return newCache;
+    });
+  };
+
+  const handleAgeSelect = (roleId: string, age: AgeCategory) => {
+    onAgeChange(roleId, age);
+    // Clear cached preview when age changes
+    const voiceId = voiceAssignments.get(roleId);
+    if (voiceId) {
+      const cacheKey = `${roleId}-${voiceId}`;
+      setAudioCache(prev => {
+        const newCache = new Map(prev);
+        newCache.delete(cacheKey);
+        return newCache;
+      });
+    }
+  };
+
+  const handlePreview = async (roleId: string) => {
+    const voiceId = voiceAssignments.get(roleId);
+    if (!voiceId) return;
+
+    const age = ageSettings.get(roleId) || 'adult';
+    const previewSpeed = AGE_SPEED_MAP[age];
+    const cacheKey = `${roleId}-${voiceId}-${age}`;
+
+    setPreviewingRole(roleId);
+
+    try {
+      // Check cache first
+      let audioUrl = audioCache.get(cacheKey);
+      
+      if (!audioUrl) {
+        // Generate new preview
+        const audioBlob = await previewVoice({
+          voice: voiceId,
+          lang: language,
+          speed: previewSpeed,
+        });
+        
+        audioUrl = URL.createObjectURL(audioBlob);
+        setAudioCache(prev => new Map(prev).set(cacheKey, audioUrl!));
+      }
+
+      // Play the audio
+      if (audioUrl) {
+        const audio = new Audio(audioUrl);
+        audio.onended = () => setPreviewingRole(null);
+        audio.onerror = () => setPreviewingRole(null);
+        await audio.play();
+      }
+    } catch (error) {
+      console.error('Preview failed:', error);
+      setPreviewingRole(null);
+    }
  };

  const handleLanguageSelect = (e: React.ChangeEvent<HTMLSelectElement>) => {
@@ -168,30 +247,91 @@ export default function VoiceAssignmentSection({

        {/* Voice Assignments */}
        <div className="space-y-5">
-          {roles.map((role, index) => (
-            <div key={role.id} className="flex flex-col sm:flex-row sm:items-center gap-4 p-6 bg-gradient-to-br from-gray-50 to-white rounded-2xl border-2 border-gray-200 hover:border-indigo-300 transition-all duration-200">
-              <div className="flex items-center gap-4 sm:w-56">
-                <div className="flex items-center justify-center w-10 h-10 bg-gradient-to-br from-indigo-500 to-purple-600 text-white rounded-xl font-bold text-sm shadow-lg shadow-indigo-500/30">
-                  {index + 1}
+          {roles.map((role, index) => {
+            const selectedAge = ageSettings.get(role.id) || 'adult';
+            const hasVoice = voiceAssignments.has(role.id);
+            const isPreviewing = previewingRole === role.id;
+            
+            return (
+              <div key={role.id} className="p-6 bg-gradient-to-br from-gray-50 to-white rounded-2xl border-2 border-gray-200 hover:border-indigo-300 transition-all duration-200">
+                {/* Header Row */}
+                <div className="flex flex-col sm:flex-row sm:items-center gap-4 mb-4">
+                  <div className="flex items-center gap-4 sm:w-56">
+                    <div className="flex items-center justify-center w-10 h-10 bg-gradient-to-br from-indigo-500 to-purple-600 text-white rounded-xl font-bold text-sm shadow-lg shadow-indigo-500/30">
+                      {index + 1}
+                    </div>
+                    <label className="font-bold text-gray-900 text-lg">
+                      {role.label}
+                    </label>
+                  </div>
+                  <select
+                    value={voiceAssignments.get(role.id) || ''}
+                    onChange={(e) => handleVoiceSelect(role.id, e.target.value)}
+                    className="flex-1 p-4 border-2 border-gray-200 rounded-xl focus:border-indigo-500 focus:ring-4 focus:ring-indigo-100 focus:outline-none bg-white text-base font-medium transition-all duration-200"
+                  >
+                    <option value="">Select a voice...</option>
+                    {KOKORO_VOICES.map((voice) => (
+                      <option key={voice.id} value={voice.id}>
+                        {voice.label}
+                      </option>
+                    ))}
+                  </select>
                </div>
-                <label className="font-bold text-gray-900 text-lg">
-                  {role.label}
-                </label>
+
+                {/* Age Category & Preview Row */}
+                {hasVoice && (
+                  <div className="flex flex-col sm:flex-row gap-4 items-start sm:items-center">
+                    {/* Age Categories */}
+                    <div className="flex-1">
+                      <label className="block text-sm font-semibold text-gray-700 mb-2">
+                        Age Category:
+                      </label>
+                      <div className="flex gap-2 flex-wrap">
+                        {(['young', 'teen', 'adult', 'old'] as AgeCategory[]).map((age) => (
+                          <button
+                            key={age}
+                            onClick={() => handleAgeSelect(role.id, age)}
+                            className={`px-4 py-2 rounded-lg font-semibold text-sm transition-all duration-200 ${
+                              selectedAge === age
+                                ? 'bg-indigo-600 text-white shadow-lg shadow-indigo-500/30'
+                                : 'bg-white text-gray-700 border-2 border-gray-200 hover:border-indigo-300'
+                            }`}
+                          >
+                            {age === 'young' && '👶 Young'}
+                            {age === 'teen' && '🧒 Teen'}
+                            {age === 'adult' && '👤 Adult'}
+                            {age === 'old' && '👴 Old'}
+                          </button>
+                        ))}
+                      </div>
+                      <p className="text-xs text-gray-500 mt-2">
+                        Speed: {AGE_SPEED_MAP[selectedAge]}x
+                      </p>
+                    </div>
+
+                    {/* Preview Button */}
+                    <button
+                      onClick={() => handlePreview(role.id)}
+                      disabled={isPreviewing || isGenerating}
+                      className="px-6 py-3 bg-green-600 text-white font-semibold rounded-xl hover:bg-green-700 disabled:opacity-50 disabled:cursor-not-allowed transition-all duration-200 flex items-center gap-2 shadow-lg shadow-green-500/30"
+                    >
+                      {isPreviewing ? (
+                        <>
+                          <div className="animate-spin rounded-full h-4 w-4 border-2 border-white border-t-transparent"></div>
+                          Playing...
+                        </>
+                      ) : (
+                        <>
+                          <span>🔊</span>
+                          Try Voice
+                        </>
+                      )}
+                    </button>
+                  </div>
+                )}
              </div>
-              <select
-                value={voiceAssignments.get(role.id) || ''}
-                onChange={(e) => handleVoiceSelect(role.id, e.target.value)}
-                className="flex-1 p-4 border-2 border-gray-200 rounded-xl focus:border-indigo-500 focus:ring-4 focus:ring-indigo-100 focus:outline-none bg-white text-base font-medium transition-all duration-200"
-              >
-                <option value="">Select a voice...</option>
-                {KOKORO_VOICES.map((voice) => (
-                  <option key={voice.id} value={voice.id}>
-                    {voice.label}
-                  </option>
-                ))}
-              </select>
-            </div>
-          ))}
+            );
+          })}
        </div>

        {/* Settings Grid */}