Update dependencies and enhance UI components for better functionality

- Added new Tauri plugins: @tauri-apps/plugin-process and @tauri-apps/plugin-updater to improve application capabilities.
- Introduced UpdateStatus component to display update information in the UI.
- Enhanced GenerationForm to include an optional instruct field for additional input.
- Refactored various components for improved styling and responsiveness, including Sidebar, AudioPlayer, and ProfileCard.
- Updated API models and schemas to accommodate new instruct parameter in generation requests and responses.
- Improved documentation for autoupdater setup and usage.

backend/database.py

@@ -39,7 +39,7 @@ class ProfileSample(Base):
 class Generation(Base):
     """Generation history database model."""
     __tablename__ = "generations"
-    
+
     id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
     profile_id = Column(String, ForeignKey("profiles.id"), nullable=False)
     text = Column(Text, nullable=False)
@@ -47,6 +47,7 @@ class Generation(Base):
     audio_path = Column(String, nullable=False)
     duration = Column(Float, nullable=False)
     seed = Column(Integer)
+    instruct = Column(Text)
     created_at = Column(DateTime, default=datetime.utcnow)
 
 

backend/history.py

@@ -28,10 +28,11 @@ async def create_generation(
     duration: float,
     seed: Optional[int],
     db: Session,
+    instruct: Optional[str] = None,
 ) -> GenerationResponse:
     """
     Create a new generation history entry.
-    
+
     Args:
         profile_id: Profile ID used for generation
         text: Generated text
@@ -40,7 +41,8 @@ async def create_generation(
         duration: Audio duration in seconds
         seed: Random seed used (if any)
         db: Database session
-        
+        instruct: Natural language instruction used (if any)
+
     Returns:
         Created generation entry
     """
@@ -52,13 +54,14 @@ async def create_generation(
         audio_path=audio_path,
         duration=duration,
         seed=seed,
+        instruct=instruct,
         created_at=datetime.utcnow(),
     )
-    
+
     db.add(db_generation)
     db.commit()
     db.refresh(db_generation)
-    
+
     return GenerationResponse.model_validate(db_generation)
 
 
@@ -139,6 +142,7 @@ async def list_generations(
             audio_path=generation.audio_path,
             duration=generation.duration,
             seed=generation.seed,
+            instruct=generation.instruct,
             created_at=generation.created_at,
         ))
     

backend/main.py

@@ -259,18 +259,19 @@ async def generate_speech(
             voice_prompt,
             data.language,
             data.seed,
+            data.instruct,
         )
-        
+
         # Calculate duration
         duration = len(audio) / sample_rate
-        
+
         # Save audio
         generation_id = str(uuid.uuid4())
         audio_path = config.get_generations_dir() / f"{generation_id}.wav"
-        
+
         from .utils.audio import save_audio
         save_audio(audio, str(audio_path), sample_rate)
-        
+
         # Create history entry
         generation = await history.create_generation(
             profile_id=data.profile_id,
@@ -280,6 +281,7 @@ async def generate_speech(
             duration=duration,
             seed=data.seed,
             db=db,
+            instruct=data.instruct,
         )
         
         return generation
@@ -342,6 +344,7 @@ async def get_generation(
         audio_path=gen.audio_path,
         duration=gen.duration,
         seed=gen.seed,
+        instruct=gen.instruct,
         created_at=gen.created_at,
     )
 

backend/migrate_add_instruct.py

@@ -0,0 +1,48 @@
+"""
+Database migration script to add instruct column to generations table.
+
+Run this once to update existing databases:
+    python -m backend.migrate_add_instruct
+"""
+
+import sqlite3
+import os
+from pathlib import Path
+
+
+def migrate():
+    """Add instruct column to generations table if it doesn't exist."""
+    # Get data directory
+    data_dir = os.environ.get("VOICEBOX_DATA_DIR")
+    if data_dir:
+        db_path = Path(data_dir) / "voicebox.db"
+    else:
+        db_path = Path.cwd() / "data" / "voicebox.db"
+
+    if not db_path.exists():
+        print(f"Database not found at {db_path}, skipping migration")
+        return
+
+    conn = sqlite3.connect(db_path)
+    cursor = conn.cursor()
+
+    # Check if instruct column already exists
+    cursor.execute("PRAGMA table_info(generations)")
+    columns = [row[1] for row in cursor.fetchall()]
+
+    if 'instruct' in columns:
+        print("instruct column already exists, skipping migration")
+        conn.close()
+        return
+
+    # Add instruct column
+    print("Adding instruct column to generations table...")
+    cursor.execute("ALTER TABLE generations ADD COLUMN instruct TEXT")
+    conn.commit()
+    conn.close()
+
+    print("Migration complete!")
+
+
+if __name__ == "__main__":
+    migrate()

backend/models.py

@@ -50,6 +50,7 @@ class GenerationRequest(BaseModel):
     language: str = Field(default="en", pattern="^(en|zh)$")
     seed: Optional[int] = Field(None, ge=0)
     model_size: Optional[str] = Field(default="1.7B", pattern="^(1\\.7B|0\\.6B)$")
+    instruct: Optional[str] = Field(None, max_length=500)
 
 
 class GenerationResponse(BaseModel):
@@ -61,6 +62,7 @@ class GenerationResponse(BaseModel):
     audio_path: str
     duration: float
     seed: Optional[int]
+    instruct: Optional[str]
     created_at: datetime
 
     class Config:
@@ -85,6 +87,7 @@ class HistoryResponse(BaseModel):
     audio_path: str
     duration: float
     seed: Optional[int]
+    instruct: Optional[str]
     created_at: datetime
 
     class Config:

backend/tts.py

@@ -241,35 +241,38 @@ class TTSModel:
         voice_prompt: dict,
         language: str = "en",
         seed: Optional[int] = None,
+        instruct: Optional[str] = None,
     ) -> Tuple[np.ndarray, int]:
         """
         Generate audio from text using voice prompt.
-        
+
         Args:
             text: Text to synthesize
             voice_prompt: Voice prompt dictionary from create_voice_prompt
             language: Language code (en or zh)
             seed: Random seed for reproducibility
-            
+            instruct: Natural language instruction for speech delivery control
+
         Returns:
             Tuple of (audio_array, sample_rate)
         """
         self.load_model()
-        
+
         # Set seed if provided
         if seed is not None:
             torch.manual_seed(seed)
             if torch.cuda.is_available():
                 torch.cuda.manual_seed(seed)
-        
+
         # Generate audio
         wavs, sample_rate = self.model.generate_voice_clone(
             text=text,
             voice_clone_prompt=voice_prompt,
+            instruct=instruct,
         )
-        
+
         audio = wavs[0]  # Get first result
-        
+
         return audio, sample_rate
     
     async def generate_from_reference(