feat transcription: update audio file upload limits to be configurable via settings, enhancing flexibility for transcription service. Update documentation to reflect new maximum file size and chunking behavior for large audio files.

.env.example

@@ -21,4 +21,6 @@ LANGCHAIN_PROJECT=routeur-ia
 # DAILY_API_KEY=61efebb10fa3956006a11e194980876c4453311ef25737fb2e434bc040326deb
 
 # PDF - logo en haut du document (section dédiée)
-PDF_LOGO_PATH=assets/logo.png
+PDF_LOGO_PATH=assets/logo.png
+
+MAX_UPLOAD_MB_AUDIO=500

api/routes/transcription.py

@@ -1,6 +1,7 @@
 """Transcription routes for audio to text conversion."""
 from fastapi import APIRouter, UploadFile, File, HTTPException, status, Depends, Query
 from typing import Optional
+from config import settings
 from core.security import get_current_user
 from domain.models import TranscriptionResponse, ErrorResponse
 from services.transcription_service import transcription_service, meeting_transcription_service
@@ -31,7 +32,7 @@ async def transcribe_meeting_audio(
 
     **Supported formats:** mp3, mp4, mpeg, mpga, m4a, wav, webm
 
-    **Max file size:** 25 MB (same limit as standard transcription)
+    **Max file size:** configurable (default 500 MB; files are chunked automatically if > 25 MB)
 
     Args:
         file: Meeting audio file upload
@@ -52,16 +53,16 @@ async def transcribe_meeting_audio(
             detail="Unsupported file format. Supported: mp3, mp4, mpeg, mpga, m4a, wav, webm",
         )
 
-    # Check file size (25 MB limit)
+    # Check file size (configurable limit; service chunks files > 25 MB)
     file.file.seek(0, 2)  # Seek to end
     file_size = file.file.tell()  # Get position (file size)
     file.file.seek(0)  # Reset to beginning
 
-    max_size = 25 * 1024 * 1024  # 25 MB
+    max_size = settings.max_upload_mb_audio * 1024 * 1024
     if file_size > max_size:
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
-            detail=f"File too large. Maximum size is 25 MB, got {file_size / (1024 * 1024):.2f} MB",
+            detail=f"File too large. Maximum size is {settings.max_upload_mb_audio} MB, got {file_size / (1024 * 1024):.2f} MB",
         )
 
     try:
@@ -93,7 +94,7 @@ async def get_supported_formats(
     """
     return {
         "supported_formats": ["mp3", "mp4", "mpeg", "mpga", "m4a", "wav", "webm"],
-        "max_file_size_mb": 25,
+        "max_file_size_mb": settings.max_upload_mb_audio,
         "model": "whisper-1",
         "languages": "Auto-detection or specify ISO-639-1 code"
     }
@@ -119,7 +120,7 @@ async def transcribe_audio(
     
     **Supported formats:** mp3, mp4, mpeg, mpga, m4a, wav, webm
     
-    **Max file size:** 25 MB (OpenAI Whisper limit)
+    **Max file size:** configurable (default 500 MB; files are chunked automatically if > 25 MB)
     
     Args:
         file: Audio file upload
@@ -140,16 +141,16 @@ async def transcribe_audio(
             detail=f"Unsupported file format. Supported: mp3, mp4, mpeg, mpga, m4a, wav, webm"
         )
     
-    # Check file size (25 MB limit for Whisper API)
+    # Check file size (configurable limit; service chunks files > 25 MB)
     file.file.seek(0, 2)  # Seek to end
     file_size = file.file.tell()  # Get position (file size)
     file.file.seek(0)  # Reset to beginning
-    
-    max_size = 25 * 1024 * 1024  # 25 MB
+
+    max_size = settings.max_upload_mb_audio * 1024 * 1024
     if file_size > max_size:
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
-            detail=f"File too large. Maximum size is 25 MB, got {file_size / (1024 * 1024):.2f} MB"
+            detail=f"File too large. Maximum size is {settings.max_upload_mb_audio} MB, got {file_size / (1024 * 1024):.2f} MB"
         )
     
     try:

config/settings.py

@@ -43,6 +43,8 @@ class Settings(BaseSettings):
     
     # Upload & chunking (PDF ingestion)
     max_upload_mb_pdf: int = 50
+    # Max audio upload size for transcription (service chunks internally; OpenAI limit is 25 MB per chunk)
+    max_upload_mb_audio: int = 500
     chunk_size: int = 1000
     chunk_overlap: int = 100
     doc_default_type: str = "project_doc"