ENCOA-295

ielts_be/services/impl/exam/listening/__init__.py

@@ -3,10 +3,9 @@ from logging import getLogger
 import random
 from typing import Dict, Any
 
-import aiofiles
 from starlette.datastructures import UploadFile
 
-from ielts_be.dtos.listening import GenerateListeningExercises, Dialog, ListeningExercises
+from ielts_be.dtos.listening import ListeningExercisesDTO, Dialog, ListeningExercises, ConversationPayload
 from ielts_be.exceptions.exceptions import TranscriptionException
 from ielts_be.repositories import IFileStorage, IDocumentStore
 from ielts_be.services import IListeningService, ILLMService, ITextToSpeechService, ISpeechToTextService
@@ -114,7 +113,16 @@ class ListeningService(IListeningService):
     async def generate_mp3(self, dto: Dialog) -> bytes:
         return await self._tts.text_to_speech(dto)
 
-    async def get_listening_question(self, dto: GenerateListeningExercises):
+    async def create_instructions(self, text: str) -> bytes:
+        script = Dialog(conversation=[ConversationPayload(**{
+            "text": text,
+            "voice": "Matthew",
+            "name": "",
+            "gender": ""
+        })])
+        return await self._tts.text_to_speech(script, False)
+
+    async def get_listening_question(self, dto: ListeningExercisesDTO):
         start_id = 1
         exercise_tasks = []
 

ielts_be/services/impl/third_parties/aws_polly.py

@@ -1,4 +1,5 @@
 import random
+from typing import Optional
 
 from aiobotocore.client import BaseClient
 
@@ -21,7 +22,7 @@ class AWSPolly(ITextToSpeechService):
         )
         return await tts_response['AudioStream'].read()
 
-    async def text_to_speech(self, dialog: Dialog) -> bytes:
+    async def text_to_speech(self, dialog: Dialog, include_final_clue = True) -> bytes:
         if not dialog.conversation and not dialog.monologue:
             raise ValueError("Unsupported argument for text_to_speech")
 
@@ -30,13 +31,14 @@ class AWSPolly(ITextToSpeechService):
         else:
             audio_segments = await self._conversation_to_speech(dialog)
 
-        final_message = await self.synthesize_speech(
-            "This audio recording, for the listening exercise, has finished.",
-            "Stephen"
-        )
+        if include_final_clue:
+            final_message = await self.synthesize_speech(
+                "This audio recording, for the listening exercise, has finished.",
+                "Stephen"
+            )
 
-        # Add finish message
-        audio_segments.append(final_message)
+            # Add finish message
+            audio_segments.append(final_message)
 
         # Combine the audio segments into a single audio file
         combined_audio = b"".join(audio_segments)