Add new sound files and update dependencies

- Added various sound files to the soundboard, including insults, quotes, and sound effects.
- Introduced new dependencies: ffmpeg-python (version 0.2.0) and pydub (version 0.25.1) for audio processing.
- Updated the lock file to reflect the new packages and their respective versions.
- Added .gitignore files in the sounds/stream and sounds/temp directories to exclude unnecessary files.

app/__init__.py

@@ -61,6 +61,9 @@ def create_app():
     # Initialize authentication service with app
     auth_service.init_app(app)
 
+    # Initialize scheduler service with app
+    scheduler_service.app = app
+
     # Start scheduler for background tasks
     scheduler_service.start()
 

app/models/__init__.py

@@ -1,7 +1,8 @@
 """Database models."""
 
 from .plan import Plan
+from .sound import Sound
 from .user import User
 from .user_oauth import UserOAuth
 
-__all__ = ["Plan", "User", "UserOAuth"]
+__all__ = ["Plan", "Sound", "User", "UserOAuth"]

app/models/sound.py

@@ -0,0 +1,225 @@
+"""Sound model for storing sound file information."""
+
+from datetime import datetime
+from enum import Enum
+from typing import Optional
+
+from app.database import db
+from sqlalchemy import Boolean, DateTime, Integer, String
+from sqlalchemy.orm import Mapped, mapped_column
+
+
+class SoundType(Enum):
+    """Sound type enumeration."""
+
+    SDB = "SDB"  # Soundboard sound
+    SAY = "SAY"  # Text-to-speech
+    STR = "STR"  # Stream sound
+
+
+class Sound(db.Model):
+    """Sound model for storing sound file information."""
+
+    __tablename__ = "sounds"
+
+    id: Mapped[int] = mapped_column(primary_key=True)
+
+    # Sound type (SDB, SAY, or STR)
+    type: Mapped[str] = mapped_column(String(3), nullable=False)
+
+    # Basic sound information
+    name: Mapped[str] = mapped_column(String(255), nullable=False)
+    filename: Mapped[str] = mapped_column(String(500), nullable=False)
+    duration: Mapped[int] = mapped_column(Integer, nullable=False)
+    size: Mapped[int] = mapped_column(Integer, nullable=False)  # Size in bytes
+    hash: Mapped[str] = mapped_column(String(64), nullable=False)  # SHA256 hash
+
+    # Normalized sound information
+    normalized_filename: Mapped[str | None] = mapped_column(
+        String(500),
+        nullable=True,
+    )
+    normalized_duration: Mapped[int | None] = mapped_column(
+        Integer,
+        nullable=True,
+    )
+    normalized_size: Mapped[int | None] = mapped_column(
+        Integer,
+        nullable=True,
+    )
+    normalized_hash: Mapped[str | None] = mapped_column(
+        String(64),
+        nullable=True,
+    )
+
+    # Sound properties
+    is_normalized: Mapped[bool] = mapped_column(
+        Boolean,
+        nullable=False,
+        default=False,
+    )
+    is_music: Mapped[bool] = mapped_column(
+        Boolean,
+        nullable=False,
+        default=False,
+    )
+    is_deletable: Mapped[bool] = mapped_column(
+        Boolean,
+        nullable=False,
+        default=True,
+    )
+
+    # Usage tracking
+    play_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+
+    # Timestamps
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime,
+        default=datetime.utcnow,
+        nullable=False,
+    )
+    updated_at: Mapped[datetime] = mapped_column(
+        DateTime,
+        default=datetime.utcnow,
+        onupdate=datetime.utcnow,
+        nullable=False,
+    )
+
+    def __repr__(self) -> str:
+        """String representation of Sound."""
+        return f"<Sound {self.name} ({self.type}) - {self.play_count} plays>"
+
+    def to_dict(self) -> dict:
+        """Convert sound to dictionary."""
+        return {
+            "id": self.id,
+            "type": self.type,
+            "name": self.name,
+            "filename": self.filename,
+            "duration": self.duration,
+            "size": self.size,
+            "hash": self.hash,
+            "normalized_filename": self.normalized_filename,
+            "normalized_duration": self.normalized_duration,
+            "normalized_size": self.normalized_size,
+            "normalized_hash": self.normalized_hash,
+            "is_normalized": self.is_normalized,
+            "is_music": self.is_music,
+            "is_deletable": self.is_deletable,
+            "play_count": self.play_count,
+            "created_at": self.created_at.isoformat(),
+            "updated_at": self.updated_at.isoformat(),
+        }
+
+    def increment_play_count(self) -> None:
+        """Increment the play count for this sound."""
+        self.play_count += 1
+        self.updated_at = datetime.utcnow()
+        db.session.commit()
+
+    def set_normalized_info(
+        self,
+        normalized_filename: str,
+        normalized_duration: float,
+        normalized_size: int,
+        normalized_hash: str,
+    ) -> None:
+        """Set normalized sound information."""
+        self.normalized_filename = normalized_filename
+        self.normalized_duration = normalized_duration
+        self.normalized_size = normalized_size
+        self.normalized_hash = normalized_hash
+        self.is_normalized = True
+        self.updated_at = datetime.utcnow()
+
+    def clear_normalized_info(self) -> None:
+        """Clear normalized sound information."""
+        self.normalized_filename = None
+        self.normalized_duration = None
+        self.normalized_hash = None
+        self.normalized_size = None
+        self.is_normalized = False
+        self.updated_at = datetime.utcnow()
+
+    def update_file_info(
+        self,
+        filename: str,
+        duration: float,
+        size: int,
+        hash_value: str,
+    ) -> None:
+        """Update file information for existing sound."""
+        self.filename = filename
+        self.duration = duration
+        self.size = size
+        self.hash = hash_value
+        self.updated_at = datetime.utcnow()
+
+    @classmethod
+    def find_by_hash(cls, hash_value: str) -> Optional["Sound"]:
+        """Find sound by hash."""
+        return cls.query.filter_by(hash=hash_value).first()
+
+    @classmethod
+    def find_by_name(cls, name: str) -> Optional["Sound"]:
+        """Find sound by name."""
+        return cls.query.filter_by(name=name).first()
+
+    @classmethod
+    def find_by_filename(cls, filename: str) -> Optional["Sound"]:
+        """Find sound by filename."""
+        return cls.query.filter_by(filename=filename).first()
+
+    @classmethod
+    def find_by_type(cls, sound_type: str) -> list["Sound"]:
+        """Find all sounds by type."""
+        return cls.query.filter_by(type=sound_type).all()
+
+    @classmethod
+    def get_most_played(cls, limit: int = 10) -> list["Sound"]:
+        """Get the most played sounds."""
+        return cls.query.order_by(cls.play_count.desc()).limit(limit).all()
+
+    @classmethod
+    def get_music_sounds(cls) -> list["Sound"]:
+        """Get all music sounds."""
+        return cls.query.filter_by(is_music=True).all()
+
+    @classmethod
+    def get_deletable_sounds(cls) -> list["Sound"]:
+        """Get all deletable sounds."""
+        return cls.query.filter_by(is_deletable=True).all()
+
+    @classmethod
+    def create_sound(
+        cls,
+        sound_type: str,
+        name: str,
+        filename: str,
+        duration: float,
+        size: int,
+        hash_value: str,
+        is_music: bool = False,
+        is_deletable: bool = True,
+        commit: bool = True,
+    ) -> "Sound":
+        """Create a new sound."""
+        # Validate sound type
+        if sound_type not in [t.value for t in SoundType]:
+            raise ValueError(f"Invalid sound type: {sound_type}")
+
+        sound = cls(
+            type=sound_type,
+            name=name,
+            filename=filename,
+            duration=duration,
+            size=size,
+            hash=hash_value,
+            is_music=is_music,
+            is_deletable=is_deletable,
+        )
+
+        db.session.add(sound)
+        if commit:
+            db.session.commit()
+        return sound

app/routes/main.py

@@ -1,6 +1,6 @@
 """Main routes for the application."""
 
-from flask import Blueprint
+from flask import Blueprint, request
 
 from app.services.decorators import (
     get_current_user,
@@ -9,6 +9,8 @@ from app.services.decorators import (
     require_role,
 )
 from app.services.scheduler_service import scheduler_service
+from app.services.sound_normalizer_service import SoundNormalizerService
+from app.services.sound_scanner_service import SoundScannerService
 
 bp = Blueprint("main", __name__)
 
@@ -101,3 +103,55 @@ def scheduler_status() -> dict:
 def manual_credit_refill() -> dict:
     """Manually trigger credit refill for all users (admin only)."""
     return scheduler_service.trigger_credit_refill_now()
+
+
+@bp.route("/admin/sounds/scan", methods=["POST"])
+@require_auth
+@require_role("admin")
+def manual_sound_scan() -> dict:
+    """Manually trigger sound directory scan (admin only)."""
+    return scheduler_service.trigger_sound_scan_now()
+
+
+@bp.route("/admin/sounds/stats")
+@require_auth
+@require_role("admin")
+def sound_statistics() -> dict:
+    """Get sound database statistics (admin only)."""
+    return SoundScannerService.get_scan_statistics()
+
+
+@bp.route("/admin/sounds/normalize/<int:sound_id>", methods=["POST"])
+@require_auth
+@require_role("admin")
+def normalize_sound(sound_id: int) -> dict:
+    """Normalize a specific sound file (admin only)."""
+    overwrite = request.args.get("overwrite", "false").lower() == "true"
+    return SoundNormalizerService.normalize_sound(sound_id, overwrite)
+
+
+@bp.route("/admin/sounds/normalize-all", methods=["POST"])
+@require_auth
+@require_role("admin")
+def normalize_all_sounds() -> dict:
+    """Normalize all soundboard files (admin only)."""
+    overwrite = request.args.get("overwrite", "false").lower() == "true"
+    limit_str = request.args.get("limit")
+    limit = int(limit_str) if limit_str else None
+    return SoundNormalizerService.normalize_all_sounds(overwrite, limit)
+
+
+@bp.route("/admin/sounds/normalization-status")
+@require_auth
+@require_role("admin")
+def normalization_status() -> dict:
+    """Get normalization status statistics (admin only)."""
+    return SoundNormalizerService.get_normalization_status()
+
+
+@bp.route("/admin/sounds/ffmpeg-check")
+@require_auth
+@require_role("admin")
+def ffmpeg_check() -> dict:
+    """Check ffmpeg availability and capabilities (admin only)."""
+    return SoundNormalizerService.check_ffmpeg_availability()

app/services/credit_service.py

@@ -14,8 +14,7 @@ class CreditService:
 
     @staticmethod
     def refill_all_users_credits() -> dict:
-        """
-        Refill credits for all active users based on their plan.
+        """Refill credits for all active users based on their plan.
         
         This function:
         1. Gets all active users
@@ -25,100 +24,101 @@ class CreditService:
         
         Returns:
             dict: Summary of the refill operation
+
         """
         try:
             # Get all active users with their plans
             users = User.query.filter_by(is_active=True).all()
-            
+
             if not users:
                 logger.info("No active users found for credit refill")
                 return {
                     "success": True,
                     "users_processed": 0,
                     "credits_added": 0,
-                    "message": "No active users found"
+                    "message": "No active users found",
                 }
-            
+
             users_processed = 0
             total_credits_added = 0
-            
+
             for user in users:
                 if not user.plan:
                     logger.warning(f"User {user.email} has no plan assigned, skipping")
                     continue
-                
+
                 # Calculate new credit amount, capped at plan max
                 current_credits = user.credits or 0
                 plan_daily_credits = user.plan.credits
                 max_credits = user.plan.max_credits
-                
+
                 # Add daily credits but don't exceed maximum
                 new_credits = min(current_credits + plan_daily_credits, max_credits)
                 credits_added = new_credits - current_credits
-                
+
                 if credits_added > 0:
                     user.credits = new_credits
                     user.updated_at = datetime.utcnow()
                     total_credits_added += credits_added
-                    
+
                     logger.debug(
                         f"User {user.email}: {current_credits} -> {new_credits} "
-                        f"(+{credits_added} credits, plan: {user.plan.code})"
+                        f"(+{credits_added} credits, plan: {user.plan.code})",
                     )
                 else:
                     logger.debug(
                         f"User {user.email}: Already at max credits "
-                        f"({current_credits}/{max_credits})"
+                        f"({current_credits}/{max_credits})",
                     )
-                
+
                 users_processed += 1
-            
+
             # Commit all changes in a single transaction
             db.session.commit()
-            
+
             logger.info(
                 f"Daily credit refill completed: {users_processed} users processed, "
-                f"{total_credits_added} total credits added"
+                f"{total_credits_added} total credits added",
             )
-            
+
             return {
                 "success": True,
                 "users_processed": users_processed,
                 "credits_added": total_credits_added,
-                "message": f"Successfully refilled credits for {users_processed} users"
+                "message": f"Successfully refilled credits for {users_processed} users",
             }
-            
+
         except Exception as e:
             # Rollback transaction on error
             db.session.rollback()
-            logger.error(f"Error during daily credit refill: {str(e)}")
-            
+            logger.error(f"Error during daily credit refill: {e!s}")
+
             return {
                 "success": False,
                 "users_processed": 0,
                 "credits_added": 0,
                 "error": str(e),
-                "message": "Credit refill failed"
+                "message": "Credit refill failed",
             }
-    
+
     @staticmethod
     def get_user_credit_info(user_id: int) -> dict:
-        """
-        Get detailed credit information for a specific user.
+        """Get detailed credit information for a specific user.
         
         Args:
             user_id: The user's ID
             
         Returns:
             dict: User's credit information
+
         """
         user = User.query.get(user_id)
         if not user:
             return {"error": "User not found"}
-        
+
         if not user.plan:
             return {"error": "User has no plan assigned"}
-        
+
         return {
             "user_id": user.id,
             "email": user.email,
@@ -127,7 +127,7 @@ class CreditService:
                 "code": user.plan.code,
                 "name": user.plan.name,
                 "daily_credits": user.plan.credits,
-                "max_credits": user.plan.max_credits
+                "max_credits": user.plan.max_credits,
             },
-            "is_active": user.is_active
-        }
+            "is_active": user.is_active,
+        }

app/services/scheduler_service.py

@@ -1,12 +1,13 @@
 """Scheduler service for managing background tasks with APScheduler."""
 
 import logging
-from typing import Optional
 
 from apscheduler.schedulers.background import BackgroundScheduler
 from apscheduler.triggers.cron import CronTrigger
+from flask import current_app
 
 from app.services.credit_service import CreditService
+from app.services.sound_scanner_service import SoundScannerService
 
 logger = logging.getLogger(__name__)
 
@@ -14,9 +15,10 @@ logger = logging.getLogger(__name__)
 class SchedulerService:
     """Service for managing scheduled background tasks."""
 
-    def __init__(self) -> None:
+    def __init__(self, app=None) -> None:
         """Initialize the scheduler service."""
-        self.scheduler: Optional[BackgroundScheduler] = None
+        self.scheduler: BackgroundScheduler | None = None
+        self.app = app
 
     def start(self) -> None:
         """Start the scheduler and add all scheduled jobs."""
@@ -25,10 +27,13 @@ class SchedulerService:
             return
 
         self.scheduler = BackgroundScheduler()
-        
+
         # Add daily credit refill job
         self._add_daily_credit_refill_job()
-        
+
+        # Add sound scanning job
+        self._add_sound_scanning_job()
+
         # Start the scheduler
         self.scheduler.start()
         logger.info("Scheduler started successfully")
@@ -47,7 +52,7 @@ class SchedulerService:
 
         # Schedule daily at 00:00 UTC
         trigger = CronTrigger(hour=0, minute=0)
-        
+
         self.scheduler.add_job(
             func=self._run_daily_credit_refill,
             trigger=trigger,
@@ -55,47 +60,99 @@ class SchedulerService:
             name="Daily Credit Refill",
             replace_existing=True,
         )
-        
+
         logger.info("Daily credit refill job scheduled for 00:00 UTC")
 
+    def _add_sound_scanning_job(self) -> None:
+        """Add the sound scanning job."""
+        if self.scheduler is None:
+            raise RuntimeError("Scheduler not initialized")
+
+        # Schedule every 5 minutes for sound scanning
+        trigger = CronTrigger(minute="*/5")
+
+        self.scheduler.add_job(
+            func=self._run_sound_scan,
+            trigger=trigger,
+            id="sound_scan",
+            name="Sound Directory Scan",
+            replace_existing=True,
+        )
+
+        logger.info("Sound scanning job scheduled every 5 minutes")
+
     def _run_daily_credit_refill(self) -> None:
         """Execute the daily credit refill task."""
         logger.info("Starting daily credit refill task")
-        
-        try:
-            result = CreditService.refill_all_users_credits()
-            
-            if result["success"]:
-                logger.info(
-                    f"Daily credit refill completed successfully: "
-                    f"{result['users_processed']} users processed, "
-                    f"{result['credits_added']} credits added"
-                )
-            else:
-                logger.error(f"Daily credit refill failed: {result['message']}")
-                
-        except Exception as e:
-            logger.exception(f"Error during daily credit refill: {e}")
+
+        app = self.app or current_app
+        with app.app_context():
+            try:
+                result = CreditService.refill_all_users_credits()
+
+                if result["success"]:
+                    logger.info(
+                        f"Daily credit refill completed successfully: "
+                        f"{result['users_processed']} users processed, "
+                        f"{result['credits_added']} credits added",
+                    )
+                else:
+                    logger.error(f"Daily credit refill failed: {result['message']}")
+
+            except Exception as e:
+                logger.exception(f"Error during daily credit refill: {e}")
+
+    def _run_sound_scan(self) -> None:
+        """Execute the sound scanning task."""
+        logger.info("Starting sound directory scan")
+
+        app = self.app or current_app
+        with app.app_context():
+            try:
+                result = SoundScannerService.scan_soundboard_directory()
+
+                if result["success"]:
+                    if result["files_added"] > 0:
+                        logger.info(
+                            f"Sound scan completed: {result['files_added']} new sounds added",
+                        )
+                    else:
+                        logger.debug("Sound scan completed: no new files found")
+                else:
+                    logger.error(f"Sound scan failed: {result.get('error', 'Unknown error')}")
+
+            except Exception as e:
+                logger.exception(f"Error during sound scan: {e}")
 
     def trigger_credit_refill_now(self) -> dict:
         """Manually trigger credit refill for testing purposes."""
         logger.info("Manually triggering credit refill")
-        return CreditService.refill_all_users_credits()
+        app = self.app or current_app
+        with app.app_context():
+            return CreditService.refill_all_users_credits()
+
+    def trigger_sound_scan_now(self) -> dict:
+        """Manually trigger sound scan for testing purposes."""
+        logger.info("Manually triggering sound scan")
+        app = self.app or current_app
+        with app.app_context():
+            return SoundScannerService.scan_soundboard_directory()
 
     def get_scheduler_status(self) -> dict:
         """Get the current status of the scheduler."""
         if self.scheduler is None:
             return {"running": False, "jobs": []}
 
-        jobs = []
-        for job in self.scheduler.get_jobs():
-            jobs.append({
+        jobs = [
+            {
                 "id": job.id,
                 "name": job.name,
-                "next_run": job.next_run_time.isoformat() 
+                "next_run": job.next_run_time.isoformat()
                           if job.next_run_time else None,
                 "trigger": str(job.trigger),
-            })
+            }
+            for job in self.scheduler.get_jobs()
+        ]
 
         return {
             "running": self.scheduler.running,
@@ -104,4 +161,4 @@ class SchedulerService:
 
 
 # Global scheduler instance
-scheduler_service = SchedulerService()
+scheduler_service = SchedulerService()

app/services/sound_normalizer_service.py

@@ -0,0 +1,491 @@
+"""Sound normalization service using ffmpeg loudnorm filter."""
+
+import hashlib
+import logging
+from pathlib import Path
+
+import ffmpeg
+from pydub import AudioSegment
+
+from app.database import db
+from app.models.sound import Sound
+
+logger = logging.getLogger(__name__)
+
+
+class SoundNormalizerService:
+    """Service for normalizing sound files using ffmpeg loudnorm."""
+
+    SUPPORTED_EXTENSIONS = {
+        ".mp3",
+        ".wav",
+        ".ogg",
+        ".flac",
+        ".m4a",
+        ".aac",
+        ".opus",
+    }
+    SOUNDS_DIR = "sounds/soundboard"
+    NORMALIZED_DIR = "sounds/normalized/soundboard"
+
+    LOUDNORM_PARAMS = {
+        "integrated": -16,
+        "true_peak": -1.5,
+        "lra": 11.0,
+        "print_format": "summary",
+    }
+
+    @staticmethod
+    def normalize_sound(sound_id: int, overwrite: bool = False) -> dict:
+        """Normalize a specific sound file using ffmpeg loudnorm.
+
+        Args:
+            sound_id: ID of the sound to normalize
+            overwrite: Whether to overwrite existing normalized file
+
+        Returns:
+            dict: Result of the normalization operation
+
+        """
+        try:
+            sound = Sound.query.get(sound_id)
+            if not sound:
+                return {
+                    "success": False,
+                    "error": f"Sound with ID {sound_id} not found",
+                }
+
+            source_path = Path(SoundNormalizerService.SOUNDS_DIR) / sound.filename
+            if not source_path.exists():
+                return {
+                    "success": False,
+                    "error": f"Source file not found: {source_path}",
+                }
+
+            # Always output as WAV regardless of input format
+            filename_without_ext = Path(sound.filename).stem
+            normalized_filename = f"{filename_without_ext}.wav"
+            normalized_path = Path(SoundNormalizerService.NORMALIZED_DIR) / normalized_filename
+
+            normalized_path.parent.mkdir(parents=True, exist_ok=True)
+
+            if normalized_path.exists() and not overwrite:
+                return {
+                    "success": False,
+                    "error": f"Normalized file already exists: {normalized_path}. Use overwrite=True to replace it.",
+                }
+
+            logger.info(
+                f"Starting normalization of {sound.name} ({sound.filename})",
+            )
+
+            result = SoundNormalizerService._normalize_with_ffmpeg(
+                str(source_path), str(normalized_path),
+            )
+
+            if result["success"]:
+                # Calculate normalized file metadata
+                normalized_metadata = (
+                    SoundNormalizerService._get_normalized_metadata(
+                        str(normalized_path),
+                    )
+                )
+
+                # Update sound record with normalized information
+                sound.set_normalized_info(
+                    normalized_filename=normalized_filename,
+                    normalized_duration=normalized_metadata["duration"],
+                    normalized_size=normalized_metadata["size"],
+                    normalized_hash=normalized_metadata["hash"],
+                )
+
+                # Commit the database changes
+                db.session.commit()
+
+                logger.info(f"Successfully normalized {sound.name}")
+                return {
+                    "success": True,
+                    "sound_id": sound_id,
+                    "sound_name": sound.name,
+                    "source_path": str(source_path),
+                    "normalized_path": str(normalized_path),
+                    "normalized_filename": normalized_filename,
+                    "normalized_duration": normalized_metadata["duration"],
+                    "normalized_size": normalized_metadata["size"],
+                    "normalized_hash": normalized_metadata["hash"],
+                    "loudnorm_stats": result.get("stats", {}),
+                }
+            return result
+
+        except Exception as e:
+            logger.error(f"Error normalizing sound {sound_id}: {e}")
+            return {"success": False, "error": str(e)}
+
+    @staticmethod
+    def normalize_all_sounds(
+        overwrite: bool = False, limit: int = None,
+    ) -> dict:
+        """Normalize all soundboard files.
+
+        Args:
+            overwrite: Whether to overwrite existing normalized files
+            limit: Maximum number of files to process (None for all)
+
+        Returns:
+            dict: Summary of the normalization operation
+
+        """
+        try:
+            query = Sound.query.filter_by(type="SDB")
+            if limit:
+                query = query.limit(limit)
+
+            sounds = query.all()
+
+            if not sounds:
+                return {
+                    "success": True,
+                    "message": "No soundboard files found to normalize",
+                    "processed": 0,
+                    "successful": 0,
+                    "failed": 0,
+                    "skipped": 0,
+                }
+
+            logger.info(f"Starting bulk normalization of {len(sounds)} sounds")
+
+            processed = 0
+            successful = 0
+            failed = 0
+            skipped = 0
+            errors = []
+
+            for sound in sounds:
+                result = SoundNormalizerService.normalize_sound(
+                    sound.id, overwrite,
+                )
+                processed += 1
+
+                if result["success"]:
+                    successful += 1
+                elif "already exists" in result.get("error", ""):
+                    skipped += 1
+                else:
+                    failed += 1
+                    errors.append(f"{sound.name}: {result['error']}")
+
+            logger.info(
+                f"Bulk normalization completed: {successful} successful, {failed} failed, {skipped} skipped",
+            )
+
+            return {
+                "success": True,
+                "message": f"Processed {processed} sounds: {successful} successful, {failed} failed, {skipped} skipped",
+                "processed": processed,
+                "successful": successful,
+                "failed": failed,
+                "skipped": skipped,
+                "errors": errors,
+            }
+
+        except Exception as e:
+            logger.error(f"Error during bulk normalization: {e}")
+            return {
+                "success": False,
+                "error": str(e),
+                "processed": 0,
+                "successful": 0,
+                "failed": 0,
+                "skipped": 0,
+            }
+
+    @staticmethod
+    def _normalize_with_ffmpeg(source_path: str, output_path: str) -> dict:
+        """Run ffmpeg loudnorm on a single file using python-ffmpeg.
+
+        Args:
+            source_path: Path to source audio file
+            output_path: Path for normalized output file (will be WAV format)
+
+        Returns:
+            dict: Result with success status and loudnorm statistics
+
+        """
+        try:
+            params = SoundNormalizerService.LOUDNORM_PARAMS
+
+            logger.debug(
+                f"Running ffmpeg normalization: {source_path} -> {output_path}",
+            )
+
+            # Create ffmpeg input stream
+            input_stream = ffmpeg.input(source_path)
+
+            # Apply loudnorm filter
+            loudnorm_filter = f"loudnorm=I={params['integrated']}:TP={params['true_peak']}:LRA={params['lra']}:print_format={params['print_format']}"
+
+            # Create output stream with WAV format
+            output_stream = ffmpeg.output(
+                input_stream,
+                output_path,
+                acodec="pcm_s16le",  # 16-bit PCM for WAV
+                ar=44100,  # 44.1kHz sample rate
+                af=loudnorm_filter,
+                y=None,  # Overwrite output file
+            )
+
+            # Run the ffmpeg process
+            out, err = ffmpeg.run(
+                output_stream, capture_stdout=True, capture_stderr=True,
+            )
+
+            # Parse loudnorm statistics from stderr
+            stats = SoundNormalizerService._parse_loudnorm_stats(
+                err.decode() if err else "",
+            )
+
+            if not Path(output_path).exists():
+                return {
+                    "success": False,
+                    "error": "Output file was not created",
+                }
+
+            return {"success": True, "stats": stats}
+
+        except ffmpeg.Error as e:
+            error_msg = (
+                f"FFmpeg error: {e.stderr.decode() if e.stderr else str(e)}"
+            )
+            logger.error(error_msg)
+            return {"success": False, "error": error_msg}
+        except Exception as e:
+            logger.error(f"Error running ffmpeg: {e}")
+            return {"success": False, "error": str(e)}
+
+    @staticmethod
+    def _parse_loudnorm_stats(stderr_output: str) -> dict:
+        """Parse loudnorm statistics from ffmpeg stderr output.
+
+        Args:
+            stderr_output: ffmpeg stderr output containing loudnorm stats
+
+        Returns:
+            dict: Parsed loudnorm statistics
+
+        """
+        stats = {}
+
+        if not stderr_output:
+            return stats
+
+        lines = stderr_output.split("\n")
+
+        for line in lines:
+            line = line.strip()
+            if "Input Integrated:" in line:
+                try:
+                    stats["input_integrated"] = float(line.split()[-2])
+                except (ValueError, IndexError):
+                    pass
+            elif "Input True Peak:" in line:
+                try:
+                    stats["input_true_peak"] = float(line.split()[-2])
+                except (ValueError, IndexError):
+                    pass
+            elif "Input LRA:" in line:
+                try:
+                    stats["input_lra"] = float(line.split()[-1])
+                except (ValueError, IndexError):
+                    pass
+            elif "Output Integrated:" in line:
+                try:
+                    stats["output_integrated"] = float(line.split()[-2])
+                except (ValueError, IndexError):
+                    pass
+            elif "Output True Peak:" in line:
+                try:
+                    stats["output_true_peak"] = float(line.split()[-2])
+                except (ValueError, IndexError):
+                    pass
+            elif "Output LRA:" in line:
+                try:
+                    stats["output_lra"] = float(line.split()[-1])
+                except (ValueError, IndexError):
+                    pass
+
+        return stats
+
+    @staticmethod
+    def _get_normalized_metadata(file_path: str) -> dict:
+        """Calculate metadata for normalized file.
+
+        Args:
+            file_path: Path to the normalized audio file
+
+        Returns:
+            dict: Metadata including duration and hash
+
+        """
+        try:
+            # Get file size
+            file_size = Path(file_path).stat().st_size
+
+            # Calculate file hash
+            file_hash = SoundNormalizerService._calculate_file_hash(file_path)
+
+            # Get duration using pydub
+            audio = AudioSegment.from_wav(file_path)
+            duration = len(audio)  # Duration in milliseconds
+
+            return {
+                "duration": duration,
+                "size": file_size,
+                "hash": file_hash,
+            }
+
+        except Exception as e:
+            logger.error(f"Error calculating metadata for {file_path}: {e}")
+            return {
+                "duration": 0,
+                "size": Path(file_path).stat().st_size,
+                "hash": "",
+            }
+
+    @staticmethod
+    def _calculate_file_hash(file_path: str) -> str:
+        """Calculate SHA256 hash of file contents."""
+        sha256_hash = hashlib.sha256()
+
+        with Path(file_path).open("rb") as f:
+            # Read file in chunks to handle large files
+            for chunk in iter(lambda: f.read(4096), b""):
+                sha256_hash.update(chunk)
+
+        return sha256_hash.hexdigest()
+
+    @staticmethod
+    def get_normalization_status() -> dict:
+        """Get statistics about normalized vs original files.
+
+        Returns:
+            dict: Statistics about normalization status
+
+        """
+        try:
+            total_sounds = Sound.query.filter_by(type="SDB").count()
+
+            normalized_count = 0
+            total_original_size = 0
+            total_normalized_size = 0
+
+            sounds = Sound.query.filter_by(type="SDB").all()
+
+            for sound in sounds:
+                original_path = Path(SoundNormalizerService.SOUNDS_DIR) / sound.filename
+
+                if original_path.exists():
+                    total_original_size += original_path.stat().st_size
+
+                # Use database field to check if normalized, not file existence
+                if sound.is_normalized and sound.normalized_filename:
+                    normalized_count += 1
+                    normalized_path = Path(SoundNormalizerService.NORMALIZED_DIR) / sound.normalized_filename
+                    if normalized_path.exists():
+                        total_normalized_size += normalized_path.stat().st_size
+
+            return {
+                "total_sounds": total_sounds,
+                "normalized_count": normalized_count,
+                "normalization_percentage": (
+                    (normalized_count / total_sounds * 100)
+                    if total_sounds > 0
+                    else 0
+                ),
+                "total_original_size": total_original_size,
+                "total_normalized_size": total_normalized_size,
+                "size_difference": (
+                    total_normalized_size - total_original_size
+                    if normalized_count > 0
+                    else 0
+                ),
+            }
+
+        except Exception as e:
+            logger.error(f"Error getting normalization status: {e}")
+            return {
+                "error": str(e),
+                "total_sounds": 0,
+                "normalized_count": 0,
+                "normalization_percentage": 0,
+            }
+
+    @staticmethod
+    def check_ffmpeg_availability() -> dict:
+        """Check if ffmpeg is available and supports loudnorm filter.
+
+        Returns:
+            dict: Information about ffmpeg availability and capabilities
+
+        """
+        try:
+            # Create a minimal test audio file to check ffmpeg
+            import tempfile
+
+            with tempfile.NamedTemporaryFile(
+                suffix=".wav", delete=False,
+            ) as temp_file:
+                temp_path = temp_file.name
+
+            try:
+                # Try a simple ffmpeg operation to check availability
+                test_input = ffmpeg.input(
+                    "anullsrc=channel_layout=stereo:sample_rate=44100",
+                    f="lavfi",
+                    t=0.1,
+                )
+                test_output = ffmpeg.output(test_input, temp_path)
+                ffmpeg.run(
+                    test_output,
+                    capture_stdout=True,
+                    capture_stderr=True,
+                    quiet=True,
+                )
+
+                # If we get here, basic ffmpeg is working
+                # Now test loudnorm filter
+                try:
+                    norm_input = ffmpeg.input(temp_path)
+                    norm_output = ffmpeg.output(
+                        norm_input,
+                        "/dev/null",
+                        af="loudnorm=I=-16:TP=-1.5:LRA=11.0",
+                        f="null",
+                    )
+                    ffmpeg.run(
+                        norm_output,
+                        capture_stdout=True,
+                        capture_stderr=True,
+                        quiet=True,
+                    )
+                    has_loudnorm = True
+                except ffmpeg.Error:
+                    has_loudnorm = False
+
+                return {
+                    "available": True,
+                    "version": "ffmpeg-python wrapper available",
+                    "has_loudnorm": has_loudnorm,
+                    "ready": has_loudnorm,
+                }
+
+            finally:
+                # Clean up temp file
+                temp_file_path = Path(temp_path)
+                if temp_file_path.exists():
+                    temp_file_path.unlink()
+
+        except Exception as e:
+            return {
+                "available": False,
+                "error": f"ffmpeg not available via python-ffmpeg: {e!s}",
+            }

app/services/sound_scanner_service.py

@@ -0,0 +1,316 @@
+"""Sound file scanning service for discovering and importing audio files."""
+
+import hashlib
+import logging
+from pathlib import Path
+
+from pydub import AudioSegment
+from pydub.utils import mediainfo
+
+from app.database import db
+from app.models.sound import Sound
+
+logger = logging.getLogger(__name__)
+
+
+class SoundScannerService:
+    """Service for scanning and importing sound files."""
+
+    # Supported audio file extensions
+    SUPPORTED_EXTENSIONS = {".mp3", ".wav", ".ogg", ".flac", ".m4a", ".aac"}
+
+    # Default soundboard directory
+    DEFAULT_SOUNDBOARD_DIR = "sounds/soundboard"
+
+    @staticmethod
+    def scan_soundboard_directory(
+        directory: str | None = None,
+    ) -> dict:
+        """Scan the soundboard directory and add new files to the database.
+
+        Args:
+            directory: Directory to scan (defaults to sounds/soundboard)
+
+        Returns:
+            dict: Summary of the scan operation
+
+        """
+        scan_dir = directory or SoundScannerService.DEFAULT_SOUNDBOARD_DIR
+
+        try:
+            # Ensure directory exists
+            scan_path = Path(scan_dir)
+            if not scan_path.exists():
+                logger.warning(
+                    f"Soundboard directory does not exist: {scan_dir}",
+                )
+                return {
+                    "success": False,
+                    "error": f"Directory not found: {scan_dir}",
+                    "files_found": 0,
+                    "files_added": 0,
+                    "files_skipped": 0,
+                }
+
+            logger.info(f"Starting soundboard scan in: {scan_dir}")
+
+            files_found = 0
+            files_added = 0
+            files_skipped = 0
+            errors = []
+
+            # Walk through directory and subdirectories
+            for file_path in scan_path.rglob("*"):
+                if file_path.is_file():
+                    filename = file_path.name
+
+                    # Check if file has supported extension
+                    if not SoundScannerService._is_supported_audio_file(
+                        filename,
+                    ):
+                        continue
+
+                    files_found += 1
+
+                    try:
+                        # Process the audio file
+                        result = SoundScannerService._process_audio_file(
+                            str(file_path),
+                            scan_dir,
+                        )
+
+                        if result["added"]:
+                            files_added += 1
+                            logger.debug(f"Added sound: {filename}")
+                        elif result.get("updated"):
+                            files_added += 1  # Count updates as additions for reporting
+                            logger.debug(f"Updated sound: {filename}")
+                        else:
+                            files_skipped += 1
+                            logger.debug(
+                                f"Skipped sound: {filename} ({result['reason']})",
+                            )
+
+                    except Exception as e:
+                        error_msg = f"Error processing {filename}: {e!s}"
+                        logger.error(error_msg)
+                        errors.append(error_msg)
+                        files_skipped += 1
+
+            # Commit all changes
+            db.session.commit()
+
+            logger.info(
+                f"Soundboard scan completed: {files_found} files found, "
+                f"{files_added} added, {files_skipped} skipped",
+            )
+
+            return {
+                "success": True,
+                "directory": scan_dir,
+                "files_found": files_found,
+                "files_added": files_added,
+                "files_skipped": files_skipped,
+                "errors": errors,
+                "message": f"Scan completed: {files_added} new sounds added",
+            }
+
+        except Exception as e:
+            db.session.rollback()
+            logger.error(f"Error during soundboard scan: {e!s}")
+
+            return {
+                "success": False,
+                "error": str(e),
+                "files_found": 0,
+                "files_added": 0,
+                "files_skipped": 0,
+                "message": "Soundboard scan failed",
+            }
+
+    @staticmethod
+    def _is_supported_audio_file(filename: str) -> bool:
+        """Check if file has a supported audio extension."""
+        return (
+            Path(filename).suffix.lower()
+            in SoundScannerService.SUPPORTED_EXTENSIONS
+        )
+
+    @staticmethod
+    def _process_audio_file(file_path: str, base_dir: str) -> dict:
+        """Process a single audio file and add it to database if new.
+
+        Args:
+            file_path: Full path to the audio file
+            base_dir: Base directory for relative path calculation
+
+        Returns:
+            dict: Processing result with added flag and reason
+
+        """
+        # Calculate file hash for deduplication
+        file_hash = SoundScannerService._calculate_file_hash(file_path)
+
+        # Get file metadata
+        metadata = SoundScannerService._extract_audio_metadata(file_path)
+
+        # Calculate relative filename from base directory
+        relative_path = Path(file_path).relative_to(Path(base_dir))
+
+        # Check if file already exists in database by hash
+        existing_sound = Sound.find_by_hash(file_hash)
+        if existing_sound:
+            return {
+                "added": False,
+                "reason": f"File already exists as '{existing_sound.name}'",
+            }
+
+        # Check if filename already exists in database
+        existing_filename_sound = Sound.find_by_filename(str(relative_path))
+        if existing_filename_sound:
+            # Remove normalized files and clear normalized info
+            SoundScannerService._clear_normalized_files(existing_filename_sound)
+            existing_filename_sound.clear_normalized_info()
+            
+            # Update existing sound with new file information
+            existing_filename_sound.update_file_info(
+                filename=str(relative_path),
+                duration=metadata["duration"],
+                size=metadata["size"],
+                hash_value=file_hash,
+            )
+            
+            return {
+                "added": False,
+                "updated": True,
+                "sound_id": existing_filename_sound.id,
+                "reason": f"Updated existing sound '{existing_filename_sound.name}' with new file data",
+            }
+
+        # Generate sound name from filename (without extension)
+        sound_name = Path(file_path).stem
+
+        # Check if name already exists and make it unique if needed
+        counter = 1
+        original_name = sound_name
+        while Sound.find_by_name(sound_name):
+            sound_name = f"{original_name}_{counter}"
+            counter += 1
+
+        # Create new sound record
+        sound = Sound.create_sound(
+            sound_type="SDB",  # Soundboard type
+            name=sound_name,
+            filename=str(relative_path),
+            duration=metadata["duration"],
+            size=metadata["size"],
+            hash_value=file_hash,
+            is_music=False,
+            is_deletable=False,
+            commit=False,  # Don't commit individually, let scanner handle transaction
+        )
+
+        return {
+            "added": True,
+            "sound_id": sound.id,
+            "reason": "New file added successfully",
+        }
+
+    @staticmethod
+    def _calculate_file_hash(file_path: str) -> str:
+        """Calculate SHA256 hash of file contents."""
+        sha256_hash = hashlib.sha256()
+
+        with Path(file_path).open("rb") as f:
+            # Read file in chunks to handle large files
+            for chunk in iter(lambda: f.read(4096), b""):
+                sha256_hash.update(chunk)
+
+        return sha256_hash.hexdigest()
+
+    @staticmethod
+    def _clear_normalized_files(sound: Sound) -> None:
+        """Remove normalized files for a sound if they exist."""
+        if sound.is_normalized and sound.normalized_filename:
+            # Import here to avoid circular imports
+            from app.services.sound_normalizer_service import SoundNormalizerService
+            
+            normalized_path = Path(SoundNormalizerService.NORMALIZED_DIR) / sound.normalized_filename
+            if normalized_path.exists():
+                try:
+                    normalized_path.unlink()
+                    logger.info(f"Removed normalized file: {normalized_path}")
+                except Exception as e:
+                    logger.warning(f"Could not remove normalized file {normalized_path}: {e}")
+
+    @staticmethod
+    def _extract_audio_metadata(file_path: str) -> dict:
+        """Extract metadata from audio file using pydub and mediainfo."""
+        try:
+            # Get file size
+            file_size = Path(file_path).stat().st_size
+
+            # Load audio file with pydub for basic info
+            audio = AudioSegment.from_file(file_path)
+
+            # Extract basic metadata from AudioSegment
+            duration = len(audio)
+            channels = audio.channels
+            sample_rate = audio.frame_rate
+
+            # Use mediainfo for more accurate bitrate information
+            bitrate = None
+            try:
+                info = mediainfo(file_path)
+                if info and "bit_rate" in info:
+                    bitrate = int(info["bit_rate"])
+                elif info and "bitrate" in info:
+                    bitrate = int(info["bitrate"])
+            except (ValueError, KeyError, TypeError):
+                # Fallback to calculated bitrate if mediainfo fails
+                if duration > 0:
+                    file_size_bits = file_size * 8
+                    bitrate = int(file_size_bits / duration / 1000)
+
+            return {
+                "duration": duration,
+                "size": file_size,
+                "bitrate": bitrate,
+                "channels": channels,
+                "sample_rate": sample_rate,
+            }
+
+        except Exception as e:
+            logger.warning(f"Could not extract metadata from {file_path}: {e}")
+            return {
+                "duration": 0,
+                "size": Path(file_path).stat().st_size,
+                "bitrate": None,
+                "channels": None,
+                "sample_rate": None,
+            }
+
+    @staticmethod
+    def get_scan_statistics() -> dict:
+        """Get statistics about sounds in the database."""
+        total_sounds = Sound.query.count()
+        sdb_sounds = Sound.query.filter_by(type="SDB").count()
+        music_sounds = Sound.query.filter_by(is_music=True).count()
+
+        # Calculate total size and duration
+        sounds = Sound.query.all()
+        total_size = sum(sound.size for sound in sounds)
+        total_duration = sum(sound.duration for sound in sounds)
+        total_plays = sum(sound.play_count for sound in sounds)
+
+        return {
+            "total_sounds": total_sounds,
+            "soundboard_sounds": sdb_sounds,
+            "music_sounds": music_sounds,
+            "total_size_bytes": total_size,
+            "total_duration": total_duration,
+            "total_plays": total_plays,
+            "most_played": [
+                sound.to_dict() for sound in Sound.get_most_played(5)
+            ],
+        }

pyproject.toml

@@ -8,11 +8,13 @@ requires-python = ">=3.12"
 dependencies = [
     "apscheduler==3.11.0",
     "authlib==1.6.0",
+    "ffmpeg-python>=0.2.0",
     "flask==3.1.1",
     "flask-cors==6.0.1",
     "flask-jwt-extended==4.7.1",
     "flask-migrate==4.1.0",
     "flask-sqlalchemy==3.1.1",
+    "pydub==0.25.1",
     "python-dotenv==1.1.1",
     "requests==2.32.4",
     "werkzeug==3.1.3",

reset.sh

@@ -1,5 +1,17 @@
 #!/bin/bash
 
+shopt -s extglob
+
 rm instance/soundboard.db
-uv run migrate_db.py init-db
+
+rm -rf alembic/versions/!(.gitignore)
+rm -rf sounds/say/!(.gitignore)
+rm -rf sounds/stream/!(.gitignore|thumbnails)
+rm -rf sounds/stream/thumbnails/!(.gitignore)
+rm -rf sounds/temp/!(.gitignore)
+rm -rf sounds/normalized/say/!(.gitignore)
+rm -rf sounds/normalized/soundboard/!(.gitignore)
+rm -rf sounds/normalized/stream/!(.gitignore)
+
+# uv run migrate_db.py init-db
 uv run main.py

sounds/normalized/.gitignore

@@ -0,0 +1,5 @@
+*
+!.gitignore
+!say
+!soundboard
+!stream

sounds/normalized/say/.gitignore

@@ -0,0 +1,2 @@
+*
+!.gitignore

sounds/normalized/soundboard/.gitignore

@@ -0,0 +1,2 @@
+*
+!.gitignore

sounds/normalized/stream/.gitignore

@@ -0,0 +1,3 @@
+*
+!.gitignore
+!thumbnails

sounds/say/.gitignore

@@ -0,0 +1,2 @@
+*
+!.gitignore