Update app.py

app.py

@@ -1,45 +1,71 @@
-# app.py (FastAPI)
 from fastapi import FastAPI, HTTPException, UploadFile, File, Form
 import subprocess
 import base64
 import os
 import uuid
 import shutil
+import whisper
 
 app = FastAPI()
 
+# Load Whisper Tiny (Fastest) once on startup
+print("Loading Whisper...")
+whisper_model = whisper.load_model("tiny")
+
+def file_to_base64(filepath):
+    if not os.path.exists(filepath): return None
+    with open(filepath, "rb") as f:
+        return base64.b64encode(f.read()).decode('utf-8')
+
 @app.post("/process-video")
-async def process_video(file: UploadFile = File(...), is_pro: bool = Form(False)):
+async def process_video(file: UploadFile = File(...)):
     job_id = str(uuid.uuid4())
     work_dir = f"/tmp/viralcat_{job_id}"
     os.makedirs(work_dir, exist_ok=True)
     video_path = os.path.join(work_dir, "video.mp4")
-    video_b64 = ""
+    audio_path = os.path.join(work_dir, "audio.wav")
     
     try:
-        # 1. Save uploaded file
         with open(video_path, "wb") as buffer:
             shutil.copyfileobj(file.file, buffer)
 
-        # 2. Check Duration
+        # 1. Get Duration
         probe = subprocess.run([
             "ffprobe", "-v", "error", "-show_entries", 
             "format=duration", "-of", "default=noprint_wrappers=1:nokey=1", 
             video_path
         ], capture_output=True, text=True, check=True)
-        
         duration = float(probe.stdout.strip() or 0)
-        if duration > 120 and not is_pro:
-            raise ValueError(f"Video is {duration:.1f}s. Free users are limited to 120s.")
 
-        # 3. Convert to Base64
-        with open(video_path, "rb") as f:
-            video_b64 = base64.b64encode(f.read()).decode('utf-8')
-        print("Done")
+        # 2. Extract exactly 15 frames regardless of length
+        # Calculate fps to get 15 frames (e.g. if 30s, fps is 15/30 = 0.5)
+        fps = 15 / max(duration, 1) 
+        subprocess.run([
+            "ffmpeg", "-y", "-i", video_path, 
+            "-vf", f"fps={fps}", 
+            "-vframes", "15",
+            "-q:v", "4", f"{work_dir}/frame_%03d.jpg"
+        ], check=True, capture_output=True)
+
+        # 3. Extract & Transcribe Audio
+        subprocess.run([
+            "ffmpeg", "-y", "-i", video_path, 
+            "-vn", "-acodec", "pcm_s16le", "-ar", "16000", "-ac", "1", audio_path
+        ], check=True, capture_output=True)
+        
+        transcript = ""
+        if os.path.exists(audio_path):
+            result = whisper_model.transcribe(audio_path)
+            transcript = result["text"].strip()
+
+        # 4. Gather frames
+        frame_files = sorted([f for f in os.listdir(work_dir) if f.startswith("frame_")])
+        frames_b64 = [file_to_base64(os.path.join(work_dir, f)) for f in frame_files]
+
         return {
             "success": True,
-            "duration": duration,
-            "video_base64": video_base64
+            "transcript": transcript,
+            "frames": frames_b64
         }
 
     except Exception as e: