Add Tauri integration and server management features. Introduced auto-start functionality for the bundled server in Tauri environment, added configuration management for data directories, and refactored backend components to utilize the new config module. Updated dependencies and improved project structure for better organization.

backend/build_binary.py

@@ -3,7 +3,6 @@ PyInstaller build script for creating standalone Python server binary.
 """
 
 import PyInstaller.__main__
-import sys
 import os
 from pathlib import Path
 
@@ -11,13 +10,30 @@ from pathlib import Path
 def build_server():
     """Build Python server as standalone binary."""
     backend_dir = Path(__file__).parent
-    
+
+    # Find qwen_tts source directory (it's an editable install)
+    qwen_tts_path = Path('/Users/jamespine/Projects/voice/Qwen3-TTS')
+
     # PyInstaller arguments
     args = [
-        'main.py',
+        'server.py',  # Use server.py as entry point instead of main.py
         '--onefile',
         '--name', 'voicebox-server',
-        '--add-data', f'utils{os.pathsep}utils',  # Include utils package
+        '--paths', str(qwen_tts_path),  # Add qwen_tts source to paths
+        '--hidden-import', 'backend',
+        '--hidden-import', 'backend.main',
+        '--hidden-import', 'backend.config',
+        '--hidden-import', 'backend.database',
+        '--hidden-import', 'backend.models',
+        '--hidden-import', 'backend.profiles',
+        '--hidden-import', 'backend.history',
+        '--hidden-import', 'backend.tts',
+        '--hidden-import', 'backend.transcribe',
+        '--hidden-import', 'backend.utils.audio',
+        '--hidden-import', 'backend.utils.cache',
+        '--hidden-import', 'backend.utils.progress',
+        '--hidden-import', 'backend.utils.hf_progress',
+        '--hidden-import', 'backend.utils.validation',
         '--hidden-import', 'torch',
         '--hidden-import', 'transformers',
         '--hidden-import', 'fastapi',
@@ -25,7 +41,15 @@ def build_server():
         '--hidden-import', 'sqlalchemy',
         '--hidden-import', 'librosa',
         '--hidden-import', 'soundfile',
-        '--collect-all', 'qwen-tts',
+        '--hidden-import', 'qwen_tts',
+        '--hidden-import', 'qwen_tts.inference',
+        '--hidden-import', 'qwen_tts.inference.qwen3_tts_model',
+        '--hidden-import', 'qwen_tts.inference.qwen3_tts_tokenizer',
+        '--hidden-import', 'qwen_tts.core',
+        '--hidden-import', 'qwen_tts.cli',
+        '--copy-metadata', 'qwen-tts',
+        '--collect-submodules', 'qwen_tts',
+        '--collect-data', 'qwen_tts',
         '--noconfirm',
         '--clean',
     ]

backend/config.py

@@ -0,0 +1,59 @@
+"""
+Configuration module for voicebox backend.
+
+Handles data directory configuration for production bundling.
+"""
+
+from pathlib import Path
+
+# Default data directory (used in development)
+_data_dir = Path("data")
+
+def set_data_dir(path: str | Path):
+    """
+    Set the data directory path.
+
+    Args:
+        path: Path to the data directory
+    """
+    global _data_dir
+    _data_dir = Path(path)
+    _data_dir.mkdir(parents=True, exist_ok=True)
+    print(f"Data directory set to: {_data_dir.absolute()}")
+
+def get_data_dir() -> Path:
+    """
+    Get the data directory path.
+
+    Returns:
+        Path to the data directory
+    """
+    return _data_dir
+
+def get_db_path() -> Path:
+    """Get database file path."""
+    return _data_dir / "voicebox.db"
+
+def get_profiles_dir() -> Path:
+    """Get profiles directory path."""
+    path = _data_dir / "profiles"
+    path.mkdir(parents=True, exist_ok=True)
+    return path
+
+def get_generations_dir() -> Path:
+    """Get generations directory path."""
+    path = _data_dir / "generations"
+    path.mkdir(parents=True, exist_ok=True)
+    return path
+
+def get_cache_dir() -> Path:
+    """Get cache directory path."""
+    path = _data_dir / "cache"
+    path.mkdir(parents=True, exist_ok=True)
+    return path
+
+def get_models_dir() -> Path:
+    """Get models directory path."""
+    path = _data_dir / "models"
+    path.mkdir(parents=True, exist_ok=True)
+    return path

backend/database.py

@@ -9,6 +9,8 @@ from datetime import datetime
 import uuid
 from pathlib import Path
 
+from . import config
+
 Base = declarative_base()
 
 
@@ -59,20 +61,25 @@ class Project(Base):
     updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
 
 
-# Database setup
-_db_path = Path("data/voicebox.db")
-_db_path.parent.mkdir(parents=True, exist_ok=True)
-
-engine = create_engine(
-    f"sqlite:///{_db_path}",
-    connect_args={"check_same_thread": False},
-)
-
-SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
+# Database setup will be initialized in init_db()
+engine = None
+SessionLocal = None
+_db_path = None
 
 
 def init_db():
     """Initialize database tables."""
+    global engine, SessionLocal, _db_path
+
+    _db_path = config.get_db_path()
+    _db_path.parent.mkdir(parents=True, exist_ok=True)
+
+    engine = create_engine(
+        f"sqlite:///{_db_path}",
+        connect_args={"check_same_thread": False},
+    )
+
+    SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
     Base.metadata.create_all(bind=engine)
 
 

backend/history.py

@@ -12,11 +12,12 @@ from sqlalchemy import or_
 
 from .models import GenerationRequest, GenerationResponse, HistoryQuery, HistoryResponse, HistoryListResponse
 from .database import Generation as DBGeneration, VoiceProfile as DBVoiceProfile
+from . import config
 
 
-# Generations storage directory
-GENERATIONS_DIR = Path("data/generations")
-GENERATIONS_DIR.mkdir(parents=True, exist_ok=True)
+def _get_generations_dir() -> Path:
+    """Get generations directory from config."""
+    return config.get_generations_dir()
 
 
 async def create_generation(

backend/main.py

@@ -17,13 +17,10 @@ import tempfile
 from pathlib import Path
 import uuid
 
-from . import database, models, profiles, history, tts, transcribe
-from .database import get_db, init_db, Generation as DBGeneration, VoiceProfile as DBVoiceProfile
+from . import database, models, profiles, history, tts, transcribe, config
+from .database import get_db, Generation as DBGeneration, VoiceProfile as DBVoiceProfile
 from .utils.progress import get_progress_manager
 
-# Initialize database
-init_db()
-
 app = FastAPI(
     title="voicebox API",
     description="Production-quality Qwen3-TTS voice cloning API",
@@ -269,7 +266,7 @@ async def generate_speech(
         
         # Save audio
         generation_id = str(uuid.uuid4())
-        audio_path = history.GENERATIONS_DIR / f"{generation_id}.wav"
+        audio_path = config.get_generations_dir() / f"{generation_id}.wav"
         
         from .utils.audio import save_audio
         save_audio(audio, str(audio_path), sample_rate)
@@ -740,10 +737,23 @@ if __name__ == "__main__":
         default=8000,
         help="Port to bind to",
     )
+    parser.add_argument(
+        "--data-dir",
+        type=str,
+        default=None,
+        help="Data directory for database, profiles, and generated audio",
+    )
     args = parser.parse_args()
 
+    # Set data directory if provided
+    if args.data_dir:
+        config.set_data_dir(args.data_dir)
+
+    # Initialize database after data directory is set
+    database.init_db()
+
     uvicorn.run(
-        "main:app",
+        "backend.main:app",
         host=args.host,
         port=args.port,
         reload=False,  # Disable reload in production

backend/profiles.py

@@ -22,11 +22,12 @@ from .database import (
 )
 from .utils.audio import validate_reference_audio, load_audio, save_audio
 from .tts import get_tts_model
+from . import config
 
 
-# Profile storage directory
-PROFILES_DIR = Path("data/profiles")
-PROFILES_DIR.mkdir(parents=True, exist_ok=True)
+def _get_profiles_dir() -> Path:
+    """Get profiles directory from config."""
+    return config.get_profiles_dir()
 
 
 async def create_profile(
@@ -58,7 +59,7 @@ async def create_profile(
     db.refresh(db_profile)
     
     # Create profile directory
-    profile_dir = PROFILES_DIR / db_profile.id
+    profile_dir = _get_profiles_dir() / db_profile.id
     profile_dir.mkdir(parents=True, exist_ok=True)
     
     return VoiceProfileResponse.model_validate(db_profile)
@@ -94,7 +95,7 @@ async def add_profile_sample(
     
     # Create sample ID and directory
     sample_id = str(uuid.uuid4())
-    profile_dir = PROFILES_DIR / profile_id
+    profile_dir = _get_profiles_dir() / profile_id
     profile_dir.mkdir(parents=True, exist_ok=True)
     
     # Copy audio file to profile directory
@@ -235,7 +236,7 @@ async def delete_profile(
     db.commit()
     
     # Delete profile directory
-    profile_dir = PROFILES_DIR / profile_id
+    profile_dir = _get_profiles_dir() / profile_id
     if profile_dir.exists():
         shutil.rmtree(profile_dir)
     

backend/server.py

@@ -0,0 +1,49 @@
+"""
+Entry point for PyInstaller-bundled voicebox server.
+
+This module provides an entry point that works with PyInstaller by using
+absolute imports instead of relative imports.
+"""
+
+import argparse
+import uvicorn
+
+# Import the FastAPI app from the backend package
+from backend.main import app
+from backend import config, database
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="voicebox backend server")
+    parser.add_argument(
+        "--host",
+        type=str,
+        default="127.0.0.1",
+        help="Host to bind to (use 0.0.0.0 for remote access)",
+    )
+    parser.add_argument(
+        "--port",
+        type=int,
+        default=8000,
+        help="Port to bind to",
+    )
+    parser.add_argument(
+        "--data-dir",
+        type=str,
+        default=None,
+        help="Data directory for database, profiles, and generated audio",
+    )
+    args = parser.parse_args()
+
+    # Set data directory if provided
+    if args.data_dir:
+        config.set_data_dir(args.data_dir)
+
+    # Initialize database after data directory is set
+    database.init_db()
+
+    uvicorn.run(
+        app,
+        host=args.host,
+        port=args.port,
+        log_level="info",
+    )

backend/tts.py

@@ -13,6 +13,7 @@ from .utils.cache import get_cache_key, get_cached_voice_prompt, cache_voice_pro
 from .utils.audio import normalize_audio
 from .utils.progress import get_progress_manager
 from .utils.hf_progress import HFProgressTracker, create_hf_progress_callback
+from . import config
 
 
 class TTSModel:
@@ -63,7 +64,7 @@ class TTSModel:
             raise ValueError(f"Unknown model size: {model_size}")
         
         # Check if model exists locally (backwards compatibility)
-        local_path = Path("data/models") / local_model_map[model_size]
+        local_path = config.get_models_dir() / local_model_map[model_size]
         if local_path.exists():
             print(f"Found local model at {local_path}")
             return str(local_path)

backend/utils/cache.py

@@ -5,12 +5,15 @@ Voice prompt caching utilities.
 import hashlib
 import torch
 from pathlib import Path
-from typing import Optional, Tuple
-import soundfile as sf
+from typing import Optional
+
+from .. import config
 
 
-_cache_dir = Path("data/cache")
-_cache_dir.mkdir(parents=True, exist_ok=True)
+def _get_cache_dir() -> Path:
+    """Get cache directory from config."""
+    return config.get_cache_dir()
+
 
 # In-memory cache
 _memory_cache: dict[str, torch.Tensor] = {}
@@ -19,21 +22,21 @@ _memory_cache: dict[str, torch.Tensor] = {}
 def get_cache_key(audio_path: str, reference_text: str) -> str:
     """
     Generate cache key from audio file and reference text.
-    
+
     Args:
         audio_path: Path to audio file
         reference_text: Reference text
-        
+
     Returns:
         Cache key (MD5 hash)
     """
     # Read audio file
     with open(audio_path, "rb") as f:
         audio_bytes = f.read()
-    
+
     # Combine audio bytes and text
     combined = audio_bytes + reference_text.encode("utf-8")
-    
+
     # Generate hash
     return hashlib.md5(combined).hexdigest()
 
@@ -43,19 +46,19 @@ def get_cached_voice_prompt(
 ) -> Optional[torch.Tensor]:
     """
     Get cached voice prompt if available.
-    
+
     Args:
         cache_key: Cache key
-        
+
     Returns:
         Cached voice prompt tensor or None
     """
     # Check in-memory cache
     if cache_key in _memory_cache:
         return _memory_cache[cache_key]
-    
+
     # Check disk cache
-    cache_file = _cache_dir / f"{cache_key}.prompt"
+    cache_file = _get_cache_dir() / f"{cache_key}.prompt"
     if cache_file.exists():
         try:
             prompt = torch.load(cache_file)
@@ -64,7 +67,7 @@ def get_cached_voice_prompt(
         except Exception:
             # Cache file corrupted, delete it
             cache_file.unlink()
-    
+
     return None
 
 
@@ -74,14 +77,14 @@ def cache_voice_prompt(
 ) -> None:
     """
     Cache voice prompt to memory and disk.
-    
+
     Args:
         cache_key: Cache key
         voice_prompt: Voice prompt tensor
     """
     # Store in memory
     _memory_cache[cache_key] = voice_prompt
-    
+
     # Store on disk
-    cache_file = _cache_dir / f"{cache_key}.prompt"
+    cache_file = _get_cache_dir() / f"{cache_key}.prompt"
     torch.save(voice_prompt, cache_file)

backend/voicebox-server.spec

@@ -0,0 +1,47 @@
+# -*- mode: python ; coding: utf-8 -*-
+from PyInstaller.utils.hooks import collect_data_files
+from PyInstaller.utils.hooks import collect_submodules
+from PyInstaller.utils.hooks import copy_metadata
+
+datas = []
+hiddenimports = ['backend', 'backend.main', 'backend.config', 'backend.database', 'backend.models', 'backend.profiles', 'backend.history', 'backend.tts', 'backend.transcribe', 'backend.utils.audio', 'backend.utils.cache', 'backend.utils.progress', 'backend.utils.hf_progress', 'backend.utils.validation', 'torch', 'transformers', 'fastapi', 'uvicorn', 'sqlalchemy', 'librosa', 'soundfile', 'qwen_tts', 'qwen_tts.inference', 'qwen_tts.inference.qwen3_tts_model', 'qwen_tts.inference.qwen3_tts_tokenizer', 'qwen_tts.core', 'qwen_tts.cli']
+datas += collect_data_files('qwen_tts')
+datas += copy_metadata('qwen-tts')
+hiddenimports += collect_submodules('qwen_tts')
+
+
+a = Analysis(
+    ['server.py'],
+    pathex=['/Users/jamespine/Projects/voice/Qwen3-TTS'],
+    binaries=[],
+    datas=datas,
+    hiddenimports=hiddenimports,
+    hookspath=[],
+    hooksconfig={},
+    runtime_hooks=[],
+    excludes=[],
+    noarchive=False,
+    optimize=0,
+)
+pyz = PYZ(a.pure)
+
+exe = EXE(
+    pyz,
+    a.scripts,
+    a.binaries,
+    a.datas,
+    [],
+    name='voicebox-server',
+    debug=False,
+    bootloader_ignore_signals=False,
+    strip=False,
+    upx=True,
+    upx_exclude=[],
+    runtime_tmpdir=None,
+    console=True,
+    disable_windowed_traceback=False,
+    argv_emulation=False,
+    target_arch=None,
+    codesign_identity=None,
+    entitlements_file=None,
+)