Add prompts to video generation and final message in listening audios.

app.py

@@ -634,7 +634,11 @@ def generate_speaking_video():
     try:
         data = request.get_json()
         avatar = data.get("avatar", random.choice(list(AvatarEnum)).value)
-        sp1_result = create_video(data["question"], avatar)
+        prompts = data.get("prompts", [])
+        question = data.get("question")
+        if len(prompts) > 0:
+            question = question + " In your answer you should consider: " + " ".join(prompts)
+        sp1_result = create_video(question, avatar)
         if sp1_result is not None:
             sound_file_path = VIDEO_FILES_PATH + sp1_result
             firebase_file_path = FIREBASE_SPEAKING_VIDEO_FILES_PATH + sp1_result
@@ -644,7 +648,7 @@ def generate_speaking_video():
 
             return {
                 "text": data["question"],
-                "prompts": data["prompts"] if "prompts" in data else [],
+                "prompts": prompts,
                 "title": data["topic"],
                 "video_url": sp1_video_url,
                 "video_path": sp1_video_path,

helper/speech_to_text_helper.py

@@ -36,6 +36,15 @@ def text_to_speech(text: str, file_name: str):
             VoiceId=voice
         )
         audio_segments.append(tts_response['AudioStream'].read())
+
+    # Add finish message
+    audio_segments.append(client.synthesize_speech(
+        Engine="neural",
+        Text="This audio recording, for the listening exercise, has finished.",
+        OutputFormat="mp3",
+        VoiceId="Stephen"
+    )['AudioStream'].read())
+
     # Combine the audio segments into a single audio file
     combined_audio = b"".join(audio_segments)
     # Save the combined audio to a single file
@@ -63,6 +72,15 @@ def conversation_text_to_speech(conversation: list, file_name: str):
             VoiceId=segment["voice"]
         )
         audio_segments.append(response['AudioStream'].read())
+
+    # Add finish message
+    audio_segments.append(client.synthesize_speech(
+        Engine="neural",
+        Text="This audio recording, for the listening exercise, has finished.",
+        OutputFormat="mp3",
+        VoiceId="Stephen"
+    )['AudioStream'].read())
+
     # Combine the audio segments into a single audio file
     combined_audio = b"".join(audio_segments)
     # Save the combined audio to a single file