Utilities for installing & setup (#31)

* Minor fixes

* Added prompts to install extras

* Added env variable creation for Azure

* Bumped version

* Minor

manim_voiceover/helper.py

@@ -3,6 +3,7 @@
 import re
 import os
 import sys
+from typing import Union
 import pip
 import textwrap
 from pydub import AudioSegment
@@ -209,3 +210,58 @@ def prompt_ask_missing_package(target_module: str, package_name: str):
         pip.main(["install", package_name])
         logger.info("Installed missing packages. Please run Manim again.")
         sys.exit(0)
+
+
+def prompt_ask_missing_extras(
+    target_module: Union[str, list],
+    extras: str,
+    dependent_item: str,
+):
+    if isinstance(target_module, str):
+        target_modules = []
+    elif isinstance(target_module, list):
+        target_modules = target_module
+    else:
+        raise TypeError("target_module must be a string or a list of strings")
+
+    try:
+        for target_module in target_modules:
+            importlib.import_module(target_module)
+        return
+    except ImportError:
+        pass
+    logger.info(
+        f"The extra packages required by {dependent_item} are not installed. "
+        f"Shall I install them for you? [Y/n]"
+    )
+    answer = input()
+    if answer.lower() == "n":
+        raise ImportError(
+            f'{extras} extras are not installed. Install them by running `pip install "manim-voiceover[{extras}]"`'
+        )
+    else:
+        logger.info(f"Installing {extras}...")
+        pip.main(["install", f"manim-voiceover[{extras}]"])
+        logger.info("Installed missing extras. Please run Manim again.")
+        sys.exit(0)
+
+
+def create_dotenv_file(required_variable_names: list, dotenv=".env"):
+    """Create a .env file with the required variables"""
+    if os.path.exists(dotenv):
+        logger.info(
+            f"File {dotenv} already exists. Would you like to overwrite it? [Y/n]"
+        )
+        answer = input()
+        if answer.lower() == "n":
+            logger.info("Skipping .env file creation...")
+            return False
+
+    logger.info("Creating .env file...")
+    with open(dotenv, "w") as f:
+        for var_name in required_variable_names:
+            logger.info(f"Enter value for {var_name}:")
+            value = input()
+            f.write(f"{var_name}={value}\n")
+
+    return True

manim_voiceover/services/azure.py

@@ -1,7 +1,12 @@
 import os
 from pathlib import Path
+import sys
 from dotenv import load_dotenv, find_dotenv
-from manim_voiceover.helper import remove_bookmarks
+from manim_voiceover.helper import (
+    create_dotenv_file,
+    prompt_ask_missing_extras,
+    remove_bookmarks,
+)
 from manim import logger
 
 try:
@@ -27,6 +32,18 @@ def serialize_word_boundary(wb):
     }
 
 
+def create_dotenv_azure():
+    logger.info(
+        "Check out https://voiceover.manim.community/en/stable/services.html#azureservice to learn how to create an account and get your subscription key."
+    )
+    if not create_dotenv_file(["AZURE_SUBSCRIPTION_KEY", "AZURE_SERVICE_REGION"]):
+        raise Exception(
+            "The environment variables AZURE_SUBSCRIPTION_KEY and AZURE_SERVICE_REGION are not set. Please set them or create a .env file with the variables."
+        )
+    logger.info("The .env file has been created. Please run Manim again.")
+    sys.exit()
+
+
 class AzureService(SpeechService):
     """Speech service for Azure TTS API."""
 
@@ -46,6 +63,10 @@ def __init__(
             output_format (str, optional): The output format to use. See the `API page <https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/rest-text-to-speech?tabs=streaming#audio-outputs>`__ for all the available options. Defaults to ``Audio48Khz192KBitRateMonoMp3``.
             prosody (dict, optional): Global prosody settings to use. See the `API page <https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-synthesis-markup#adjust-prosody>`__ for all the available options. Defaults to None.
         """
+        prompt_ask_missing_extras(
+            "azure.cognitiveservices.speech", "azure", "AzureService"
+        )
+
         self.voice = voice
         self.style = style
         self.output_format = output_format
@@ -63,12 +84,9 @@ def generate_from_text(
             cache_dir = self.cache_dir
 
         # Apply prosody
-        prosody = self.prosody
-        if "prosody" in kwargs:
-            prosody = kwargs["prosody"]
+        prosody = kwargs.get("prosody", self.prosody)
 
         if prosody is not None:
-            prosody = kwargs["prosody"]
             if not isinstance(prosody, dict):
                 raise ValueError(
                     "The prosody argument must be a dict that contains at least one of the following keys: 'pitch', 'contour', 'range', 'rate', 'volume'."
@@ -127,9 +145,10 @@ def generate_from_text(
             azure_subscription_key = os.environ["AZURE_SUBSCRIPTION_KEY"]
             azure_service_region = os.environ["AZURE_SERVICE_REGION"]
         except KeyError:
-            raise Exception(
-                "Microsoft Azure's text-to-speech API needs account credentials to connect. You can create an account for free and (as of writing this) get a free quota of TTS minutes. Check out the documentation for instructions."
+            logger.error(
+                "Could not find the environment variables AZURE_SUBSCRIPTION_KEY and AZURE_SERVICE_REGION. Microsoft Azure's text-to-speech API needs account credentials to connect. You can create an account for free and (as of writing this) get a free quota of TTS minutes."
             )
+            create_dotenv_azure()
 
         speech_config = speechsdk.SpeechConfig(
             subscription=azure_subscription_key,
@@ -185,6 +204,16 @@ def process_event(evt):
                     logger.error(
                         "Error details: {}".format(cancellation_details.error_details)
                     )
+                    if "authentication" in cancellation_details.error_details.lower():
+                        logger.error(
+                            "The authentication credentials are invalid. Please check the environment variables AZURE_SUBSCRIPTION_KEY and AZURE_SERVICE_REGION."
+                        )
+                        logger.info(
+                            "Would you like to enter new values for the variables in the .env file? [Y/n]"
+                        )
+                        if input().lower() in ["y", "yes", ""]:
+                            create_dotenv_azure()
+
             raise Exception("Speech synthesis failed")
 
         return json_dict

manim_voiceover/services/coqui/synthesize.py

@@ -10,9 +10,7 @@
     from TTS.utils.manage import ModelManager
     from .utils_synthesizer import Synthesizer
 except ImportError:
-    logger.error(
-        'Missing packages. Run `pip install TTS` to use CoquiService.'
-    )
+    logger.error("Missing packages. Run `pip install TTS` to use CoquiService.")
 
 DEFAULT_MODEL = "tts_models/en/ljspeech/tacotron2-DDC"
 

manim_voiceover/services/gtts.py

@@ -1,12 +1,12 @@
 from pathlib import Path
 from manim import logger
-from manim_voiceover.helper import remove_bookmarks
+from manim_voiceover.helper import prompt_ask_missing_extras, remove_bookmarks
 
 try:
     from gtts import gTTS, gTTSError
 except ImportError:
     logger.error(
-        'Missing packages. Run `pip install "manim-voiceover[gtts]"` to use GoogleService.'
+        'Missing packages. Run `pip install "manim-voiceover[gtts]"` to use GTTSService.'
     )
 
 from manim_voiceover.services.base import SpeechService
@@ -26,6 +26,7 @@ def __init__(self, lang="en", tld="com", **kwargs):
                 for all the available options. Defaults to "en".
             tld (str, optional): Top level domain of the Google Translate URL. Defaults to "com".
         """
+        prompt_ask_missing_extras("gtts", "gtts", "GTTSService")
         SpeechService.__init__(self, **kwargs)
         self.lang = lang
         self.tld = tld

manim_voiceover/services/pyttsx3.py

@@ -1,11 +1,12 @@
 from pathlib import Path
 from manim import logger
+from manim_voiceover.helper import prompt_ask_missing_extras
 
 try:
     from pyttsx3 import Engine
 except ImportError:
     logger.error(
-        'Missing packages. Run `pip install "manim-voiceover[pyttsx3]"` to use Pyttsx3Service.'
+        'Missing packages. Run `pip install "manim-voiceover[pyttsx3]"` to use PyTTSX3Service.'
     )
 
 from manim_voiceover.services.base import SpeechService
@@ -16,6 +17,8 @@ class PyTTSX3Service(SpeechService):
 
     def __init__(self, engine=None, **kwargs):
         """"""
+        prompt_ask_missing_extras("pyttsx3", "pyttsx3", "PyTTSX3Service")
+
         if engine is None:
             engine = Engine()
 

manim_voiceover/services/recorder/__init__.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-from manim_voiceover.helper import msg_box, remove_bookmarks
+from manim_voiceover.helper import msg_box, prompt_ask_missing_extras, remove_bookmarks
 
 from manim_voiceover.services.base import SpeechService
 from manim import logger
@@ -47,6 +47,10 @@ def __init__(
             trim_buffer_start (int, optional): Buffer duration for trimming silence at the start. Defaults to 200 ms.
             trim_buffer_end (int, optional): Buffer duration for trimming silence at the end. Defaults to 200 ms.
         """
+        prompt_ask_missing_extras(
+            ["pyaudio", "pynput", "playsound"], "recorder", "RecorderService"
+        )
+
         self.recorder = Recorder(
             format=format,
             channels=channels,

manim_voiceover/services/recorder/utility.py

@@ -9,14 +9,9 @@
 
 from manim_voiceover.helper import trim_silence, wav2mp3
 
-try:
-    from pynput import keyboard
-    import pyaudio
-    import playsound
-except ImportError:
-    logger.error(
-        'Missing packages. Run `pip install "manim-voiceover[recorder]"` to use RecorderService.'
-    )
+from pynput import keyboard
+import pyaudio
+import playsound
 
 
 class MyListener(keyboard.Listener):

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "manim-voiceover"
-version = "0.2.1.post0"
+version = "0.2.1.post1"
 description = "Manim plugin for all things voiceover"
 authors = ["The Manim Community Developers <[email protected]>"]
 license = "MIT"