Squashed 'utils_v2/' content from commit 93bfec2

git-subtree-dir: utils_v2 git-subtree-split: 93bfec28ca0596abf5b4e126dd31d7934908083e
2024-12-04 11:41:40 +05:30
commit 0b791f7a1d
131 changed files with 101581 additions and 0 deletions
@@ -0,0 +1,175 @@
+"""
+
+    AUTHOR:
+
+        Khushal P Soonderji
+
+    DATE:
+
+        Thursday, 26th Sept., 2024
+
+    OBJECTIVE:
+
+        To provide a fast way to make audio from TTS engines.
+
+    REFERENCES:
+
+        01. Usage: https://github.com/myshell-ai/MeloTTS/blob/main/docs/install.md#python-api
+        02. Installation: https://github.com/myshell-ai/MeloTTS/blob/main/docs/install.md#linux-and-macos-install
+
+    DOWNLOADS:
+
+        N/A
+
+"""
+
+
+#   *****************************************************************************************************************
+#  *****                                                                                                          ****
+# ***                                                   IMPORT                                                      ***
+#  *****                                                                                                          ****
+#   *****************************************************************************************************************
+
+
+# To make sibling directories accessible for imports:
+import sys
+sys.path.append(".")
+sys.path.append("..")
+
+# System-level activities:
+import io
+
+# To use the AI:
+from melo.api import TTS
+import numpy as np
+import soundfile
+
+
+#   *****************************************************************************************************************
+#  *****                                                                                                          ****
+# ***                                           MACROS / ONE-TIME INIT                                              ***
+#  *****                                                                                                          ****
+#   *****************************************************************************************************************
+
+
+# --- Nothing Yet
+
+
+#   *****************************************************************************************************************
+#  *****                                                                                                          ****
+# ***                                                VARIABLES                                                      ***
+#  *****                                                                                                          ****
+#   *****************************************************************************************************************
+
+
+# --- Nothing Yet
+
+
+#   *****************************************************************************************************************
+#  *****                                                                                                          ****
+# ***                                                  CLASSES                                                      ***
+#  *****                                                                                                          ****
+#   *****************************************************************************************************************
+
+
+class EasyTTS:
+
+    __sampling_rate = 44_100
+
+    def __init__(
+            self,
+            language = "EN",
+            speed = 1.0
+    ):
+
+        self.__audio = np.zeros(1)
+        self.__language = language
+        self.__speed = speed
+        self.__model = TTS(language = language, device = "auto")
+        self.__speakers = self.__model.hps.data.spk2id
+
+    def list_speakers(self):
+        return list(self.__speakers.keys())
+
+    def speak(
+            self,
+            text,
+            speaker
+    ):
+
+        this_audio = self.__model.tts_to_file(
+            text,
+            self.__speakers[speaker],
+            speed = self.__speed,
+            quiet = True
+        )
+
+        self.__audio = np.concatenate((self.__audio, this_audio))
+
+    def pause(self, seconds):
+
+        self.__audio = np.concatenate((
+            self.__audio,
+            np.zeros(int(self.__sampling_rate * seconds))
+        ))
+
+    def to_wav(self, path = None):
+
+        if path is None:
+            audio_buffer = io.BytesIO()
+            soundfile.write(audio_buffer, self.__audio, self.__sampling_rate)
+            return audio_buffer
+
+        else: soundfile.write(path, self.__audio, self.__sampling_rate)
+
+
+#   *****************************************************************************************************************
+#  *****                                                                                                          ****
+# ***                                               MAIN PROGRAM                                                    ***
+#  *****                                                                                                          ****
+#   *****************************************************************************************************************
+
+
+if __name__ == "__main__":
+
+    speaker = "EN-BR"
+    tts_maker = EasyTTS(language = "EN", speed = 0.9)
+
+    tts_maker.speak(
+        text = """
+            Imagine delighting your doctors with a personalized calendar,  
+            crafted from their own cherished memories.
+            """,
+        speaker = speaker
+    )
+    tts_maker.pause(seconds = 0.3)
+    tts_maker.speak(
+        text = """
+            Every day, as they turn the page,  
+            they’ll not only relive those special moments but also remember you, 
+            the one who made it happen.
+            """,
+        speaker = speaker
+    )
+    tts_maker.pause(seconds = 0.75)
+    tts_maker.speak(
+        text = "STEP 1:",
+        speaker = speaker
+    )
+    tts_maker.pause(seconds = 0.3)
+    tts_maker.speak(
+        text = "Start by identifying the doctors you’d like to engage with, and add them to our app.",
+        speaker = speaker
+    )
+    tts_maker.pause(seconds = 0.3)
+    tts_maker.speak(
+        text = "No rush, you can add their photographs later as well.",
+        speaker = speaker
+    )
+    tts_maker.pause(seconds = 0.3)
+    tts_maker.speak(
+        text = "With this, your engagement funnel is created.",
+        speaker = speaker
+    )
+
+    tts_maker.to_wav(r"/home/developer/Downloads/voiceover.wav")