fix(GenerationContext.py): fix typo in variable name powerfulllmengine to powerfulllmengine for better readability

feat(GenerationContext.py): add setup_dir method to create a directory for output files with a timestamp
feat(GenerationContext.py): call setup_dir method before generating script and synthesizing audio to ensure output directory exists
feat(prompts/fix_captions.yaml): add a new prompt file to provide instructions for fixing captions
fix(BaseTTSEngine.py): add force_duration method to adjust audio clip duration if it exceeds a specified duration
feat(CoquiTTSEngine.py): add options for forcing duration and specifying duration in the UI
feat(utils/prompting.py): add get_prompt function to load prompt files from a specified location
fix(gradio_ui.py): set equal_height=True for engine_rows to ensure consistent height for engine options

src/engines/TTSEngine/BaseTTSEngine.py

@@ -1,10 +1,23 @@
+import moviepy.editor as mp
 from abc import ABC, abstractmethod
+# Assuming BaseEngine is defined elsewhere in your project
 from ..BaseEngine import BaseEngine
 
 
 class BaseTTSEngine(BaseEngine):
-    pass
 
     @abstractmethod
     def synthesize(self, text: str, path: str) -> str:
         pass
+    
+    def force_duration(self, duration: float, path: str):
+        audio_clip = mp.AudioFileClip(path)
+        
+        if audio_clip.duration > duration:
+            speed_factor = audio_clip.duration / duration
+            
+            new_audio = audio_clip.fx(mp.vfx.speedx, speed_factor, final_duration=duration)
+            
+            new_audio.write_audiofile(path, codec='libmp3lame')
+            
+        audio_clip.close()

src/engines/TTSEngine/CoquiTTSEngine.py

@@ -90,13 +90,15 @@ class CoquiTTSEngine(BaseTTSEngine):
         "ko",  # Korean
         "hi",  # Hindi
     ]
-    num_options = 2
+    num_options = 4
 
     def __init__(self, options: list):
         super().__init__()
 
         self.voice = options[0][0]
         self.language = options[1][0]
+        self.to_force_duration = options[2][0]
+        self.duration = options[3]
 
         os.environ["COQUI_TOS_AGREED"] = "1"
 
@@ -106,11 +108,13 @@ class CoquiTTSEngine(BaseTTSEngine):
 
     def synthesize(self, text: str, path: str) -> str:
         #      self.tts.tts_to_file(text=text, file_path=path, lang=self.language, speaker=self.voice)
+        if self.to_force_duration:
+            self.force_duration(float(self.duration), path)
         return path
 
     @classmethod
     def get_options(cls) -> list:
-        return [
+        options = [
             gr.Dropdown(
                 label="Voice",
                 choices=cls.voices,
@@ -124,3 +128,13 @@ class CoquiTTSEngine(BaseTTSEngine):
                 value=cls.languages[0],
             ),
         ]
+    
+        duration_checkbox = gr.Checkbox(value=False)
+        duration = gr.Number(label="Duration", value=57, step=1, minimum=10, visible=False)
+        duration_switch = lambda x: gr.update(visible=x)
+        duration_checkbox.change(duration_switch, inputs=[duration_checkbox], outputs=[duration])
+        duration_checkbox_group = gr.CheckboxGroup([duration_checkbox], label="Force duration")
+
+        options.append(duration_checkbox_group)
+        options.append(duration)
+        return options