yta-audio-narration 0.0.1__tar.gz → 0.0.2__tar.gz

{yta_audio_narration-0.0.1 → yta_audio_narration-0.0.2}/PKG-INFO

@@ -1,15 +1,16 @@
 Metadata-Version: 2.3
 Name: yta-audio-narration
-Version: 0.0.1
+Version: 0.0.2
 Summary: Youtube Autonomous Audio Narration Module.
 Author: danialcala94
 Author-email: danielalcalavalera@gmail.com
 Requires-Python: ==3.9
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
-Requires-Dist: coqui-tts (>=0.25.3,<0.26.0)
 Requires-Dist: gtts (>=2.5.1,<3.0.0)
 Requires-Dist: pyttsx3 (>=2.90,<3.0)
+Requires-Dist: yta_audio_narration_common (>=0.0.1,<1.0.0)
+Requires-Dist: yta_audio_narration_coqui (>=0.0.1,<1.0.0)
 Requires-Dist: yta_constants (>=0.0.1,<1.0.0)
 Requires-Dist: yta_file (>=0.0.1,<1.0.0)
 Requires-Dist: yta_file_downloader (>=0.0.1,<1.0.0)

{yta_audio_narration-0.0.1 → yta_audio_narration-0.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "yta-audio-narration"
-version = "0.0.1"
+version = "0.0.2"
 description = "Youtube Autonomous Audio Narration Module."
 authors = [
     {name = "danialcala94",email = "danielalcalavalera@gmail.com"}
@@ -8,6 +8,7 @@ authors = [
 readme = "README.md"
 requires-python = "==3.9"
 dependencies = [
+    "yta_audio_narration_common (>=0.0.1,<1.0.0)",
     "yta_validation (>=0.0.1,<1.0.0)",
     "yta_constants (>=0.0.1,<1.0.0)",
     "yta_programming (>=0.0.1,<1.0.0)",
@@ -19,9 +20,9 @@ dependencies = [
     # is also needed for the open_voice voice that has
     # been commented
     #"torch (>=2.3.0,<3.0.0)",
-    # Careful, 'coqui-tts' v0.26.0 drops Python 3.9
-    # support. Do we actually use it (?)
-    "coqui-tts (>=0.25.3,<0.26.0)",
+    # TODO: Maybe these specific modules can be
+    # optional...
+    "yta_audio_narration_coqui (>=0.0.1,<1.0.0)",
     "pyttsx3 (>=2.90,<3.0)",
     "gtts (>=2.5.1,<3.0.0)",
 ]

yta_audio_narration-0.0.2/src/yta_audio_narration/__init__.py

@@ -0,0 +1,10 @@
+"""
+Welcome to Youtube Autonomous Audio Narration
+Module.
+
+This module is based on the voice narration
+modules that are specific for each voice
+available for our system. Check libs like
+'yta_audio_narration_coqui' for specific
+voices.
+"""

yta_audio_narration-0.0.2/src/yta_audio_narration/enums.py

@@ -0,0 +1,130 @@
+from yta_audio_narration_common.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
+from yta_constants.enum import YTAEnum as Enum
+from typing import Union
+
+
+# TODO: Is this 'VoiceNarrationEngine' actually
+# being used (?)
+class VoiceNarrationEngine(Enum):
+    """
+    The engines we have available for voice narration
+    generation.
+    """
+
+    DEFAULT = 'default'
+    """
+    When this option is provided, the system will
+    choose one of the available enum elements.
+    """
+    COQUI = 'coqui'
+    GOOGLE = 'google'
+    MICROSOFT = 'microsoft'
+    OPEN_VOICE = 'open_voice'
+    TETYYS = 'tetyys'
+    TIKTOK = 'tiktok'
+    TORTOISE = 'tortoise'
+    TTSMP3 = 'ttsmp3'
+
+    def _get_engine(
+        self
+    ) -> 'VoiceNarrationEngine':
+        """
+        We turn the DEFAULT instance into a specific
+        one to simplify the way we handle the options.
+
+        For internal use only.
+        """
+        return (
+            VoiceNarrationEngine.GOOGLE
+            if self is VoiceNarrationEngine.DEFAULT else
+            self
+        )
+
+    def get_voice_narrator_class(
+        self
+    # ) -> Union['CoquiVoiceNarrator', 'GoogleVoiceNarrator', 'MicrosoftVoiceNarrator', 'OpenVoiceVoiceNarrator', 'TetyysVoiceNarrator', 'TiktokVoiceNarrator', 'TortoiseVoiceNarrator', 'Ttsmp3VoiceNarrator']:
+    ) -> Union['CoquiVoiceNarrator', 'GoogleVoiceNarrator', 'MicrosoftVoiceNarrator', 'TetyysVoiceNarrator', 'TiktokVoiceNarrator', 'TortoiseVoiceNarrator', 'Ttsmp3VoiceNarrator']:
+        """
+        Get the VoiceNarrator class associated with this
+        enum instance.
+        """
+        # from yta_audio.voice.generation.narrator import CoquiVoiceNarrator, GoogleVoiceNarrator, MicrosoftVoiceNarrator, OpenVoiceVoiceNarrator, TetyysVoiceNarrator, TiktokVoiceNarrator, TortoiseVoiceNarrator, Ttsmp3VoiceNarrator
+        from yta_audio.voice.generation.narrator import CoquiVoiceNarrator, GoogleVoiceNarrator, MicrosoftVoiceNarrator, TetyysVoiceNarrator, TiktokVoiceNarrator, TortoiseVoiceNarrator, Ttsmp3VoiceNarrator
+
+        engine = self._get_engine()
+
+        return {
+            VoiceNarrationEngine.GOOGLE: GoogleVoiceNarrator,
+            VoiceNarrationEngine.COQUI: CoquiVoiceNarrator,
+            VoiceNarrationEngine.MICROSOFT: MicrosoftVoiceNarrator,
+            # VoiceNarrationEngine.OPEN_VOICE: OpenVoiceVoiceNarrator,
+            VoiceNarrationEngine.TETYYS: TetyysVoiceNarrator,
+            VoiceNarrationEngine.TIKTOK: TiktokVoiceNarrator,
+            VoiceNarrationEngine.TORTOISE: TortoiseVoiceNarrator,
+            VoiceNarrationEngine.TTSMP3: Ttsmp3VoiceNarrator,
+        }[engine]
+    
+    @property
+    def available_languages(
+        self
+    ) -> list[NarrationLanguage]:
+        return self.get_voice_narrator_class().get_available_languages()
+    
+    def is_language_valid(
+        self,
+        language: NarrationLanguage
+    ) -> bool:
+        """
+        Check if the given 'language' is accepted by
+        this engine.
+        """
+        return NarrationLanguage.to_enum(language) in self.available_languages
+    
+    def get_available_narrator_names(
+        self,
+        language: NarrationLanguage
+    ) -> list[str]:
+        return self.get_voice_narrator_class().get_available_narrator_names(language)
+    
+    def is_narrator_name_valid(
+        self,
+        language: NarrationLanguage,
+        narration_name: str
+    ) -> bool:
+        return narration_name in self.get_available_narrator_names(language)
+
+    @property
+    def available_emotions(
+        self
+    ) -> list[VoiceEmotion]:
+        return self.get_voice_narrator_class().get_available_emotions()
+    
+    def is_emotion_valid(
+        self,
+        emotion: VoiceEmotion
+    ) -> bool:
+        return VoiceEmotion.to_enum(emotion) in self.available_emotions
+
+    @property
+    def available_speeds(
+        self
+    ) -> list[VoiceSpeed]:
+        return self.get_voice_narrator_class().get_available_speeds()
+    
+    def is_speed_valid(
+        self,
+        speed: VoiceSpeed
+    ) -> bool:
+        return VoiceSpeed.to_enum(speed) in self.available_speeds
+    
+    @property
+    def available_pitches(
+        self
+    ) -> list[VoicePitch]:
+        return self.get_voice_narrator_class().get_available_pitches()
+    
+    def is_pitch_valid(
+        self,
+        pitch: VoicePitch
+    ) -> bool:
+        return VoicePitch.to_enum(pitch) in self.available_pitches

{yta_audio_narration-0.0.1 → yta_audio_narration-0.0.2}/src/yta_audio_narration/narrator.py

@@ -1,5 +1,5 @@
-from yta_audio_narration.voice import NarrationVoice
-from yta_audio_narration.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
+from yta_audio_narration_common.voice import NarrationVoice
+from yta_audio_narration_common.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
 from yta_audio_narration.voices.coqui import narrate as narrate_coqui, CoquiNarrationVoice, LANGUAGE_OPTIONS as COQUI_LANGUAGE_OPTIONS, get_narrator_names_by_language as get_coqui_narrator_names_by_language, EMOTION_OPTIONS as COQUI_EMOTION_OPTIONS, SPEED_OPTIONS as COQUI_SPEED_OPTIONS, PITCH_OPTIONS as COQUI_PITCH_OPTIONS, CoquiVoiceName
 from yta_audio_narration.voices.google import narrate as narrate_google, GoogleNarrationVoice, LANGUAGE_OPTIONS as GOOGLE_LANGUAGE_OPTIONS, get_narrator_names_by_language as get_google_narrator_names_by_language, EMOTION_OPTIONS as GOOGLE_EMOTION_OPTIONS, SPEED_OPTIONS as GOOGLE_SPEED_OPTIONS, PITCH_OPTIONS as GOOGLE_PITCH_OPTIONS, GoogleTld
 from yta_audio_narration.voices.microsoft import narrate as narrate_microsoft, MicrosoftNarrationVoice, LANGUAGE_OPTIONS as MICROSOFT_LANGUAGE_OPTIONS, get_narrator_names_by_language as get_microsoft_narrator_names_by_language, EMOTION_OPTIONS as MICROSOFT_EMOTION_OPTIONS, SPEED_OPTIONS as MICROSOFT_SPEED_OPTIONS, PITCH_OPTIONS as MICROSOFT_PITCH_OPTIONS, MicrosoftVoiceName

yta_audio_narration-0.0.2/src/yta_audio_narration/voices/coqui.py

@@ -0,0 +1,6 @@
+"""
+TODO: Do we make this optional or not? If it
+is optional we can allow installing the libs
+only if using this one.
+"""
+from yta_audio_narration_coqui import CoquiVoiceName, LANGUAGE_OPTIONS, EMOTION_OPTIONS, SPEED_OPTIONS, PITCH_OPTIONS, CoquiNarrationVoice, get_narrator_names_by_language, narrate, narrate_imitating_voice

{yta_audio_narration-0.0.1 → yta_audio_narration-0.0.2}/src/yta_audio_narration/voices/google.py

@@ -7,9 +7,9 @@ You have a lot of information here:
 - https://pypi.org/project/langcodes/
 - https://gtts.readthedocs.io/en/latest/module.html#languages-gtts-lang
 """
-from yta_audio_narration.consts import DEFAULT_VOICE
-from yta_audio_narration.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
-from yta_audio_narration.voice import NarrationVoice
+from yta_audio_narration_common.consts import DEFAULT_VOICE
+from yta_audio_narration_common.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
+from yta_audio_narration_common.voice import NarrationVoice
 from yta_constants.enum import YTAEnum as Enum
 from yta_constants.file import FileType
 from yta_programming.output import Output

{yta_audio_narration-0.0.1 → yta_audio_narration-0.0.2}/src/yta_audio_narration/voices/microsoft.py

@@ -1,6 +1,6 @@
-from yta_audio_narration.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
-from yta_audio_narration.consts import DEFAULT_VOICE
-from yta_audio_narration.voice import NarrationVoice
+from yta_audio_narration_common.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
+from yta_audio_narration_common.consts import DEFAULT_VOICE
+from yta_audio_narration_common.voice import NarrationVoice
 from yta_constants.enum import YTAEnum as Enum
 from yta_constants.file import FileType
 from yta_programming.output import Output

{yta_audio_narration-0.0.1 → yta_audio_narration-0.0.2}/src/yta_audio_narration/voices/open_voice.py

@@ -1,6 +1,6 @@
-# from yta_audio_narration.consts import DEFAULT_VOICE
-# from yta_audio_narration.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
-# from yta_audio_narration.voice import NarrationVoice
+# from yta_audio_narration_common.consts import DEFAULT_VOICE
+# from yta_audio_narration_common.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
+# from yta_audio_narration_common.voice import NarrationVoice
 # from yta_programming.path import DevPathHandler
 # from yta_constants.enum import YTAEnum as Enum
 # from yta_programming.output import Output

{yta_audio_narration-0.0.1 → yta_audio_narration-0.0.2}/src/yta_audio_narration/voices/tetyys.py

@@ -9,9 +9,9 @@ some examples of this:
 'Female Whisper' p: 169, s: 140
 'Mary' p: 169, s: 140
 """
-from yta_audio_narration.consts import DEFAULT_VOICE
-from yta_audio_narration.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
-from yta_audio_narration.voice import NarrationVoice
+from yta_audio_narration_common.consts import DEFAULT_VOICE
+from yta_audio_narration_common.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
+from yta_audio_narration_common.voice import NarrationVoice
 from yta_file.handler import FileHandler
 from yta_constants.enum import YTAEnum as Enum
 from yta_constants.file import FileType

{yta_audio_narration-0.0.1 → yta_audio_narration-0.0.2}/src/yta_audio_narration/voices/tiktok.py

@@ -7,9 +7,9 @@ And you have more projects here:
 - Pproject to use Tiktok API and session id (https://github.com/oscie57/tiktok-voice)
 - Project that is install and play (I think) https://github.com/Giooorgiooo/TikTok-Voice-TTS/blob/main/tiktokvoice.py
 """
-from yta_audio_narration.consts import DEFAULT_VOICE
-from yta_audio_narration.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
-from yta_audio_narration.voice import NarrationVoice
+from yta_audio_narration_common.consts import DEFAULT_VOICE
+from yta_audio_narration_common.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
+from yta_audio_narration_common.voice import NarrationVoice
 from yta_text.handler import TextHandler
 from yta_file.handler import FileHandler
 from yta_constants.enum import YTAEnum as Enum

{yta_audio_narration-0.0.1 → yta_audio_narration-0.0.2}/src/yta_audio_narration/voices/tortoise.py

@@ -13,9 +13,9 @@ https://github.com/idiap/coqui-ai-TTS with
 a new version that is maintained, and the 
 'tts' was generating conflicts.
 """
-from yta_audio_narration.consts import DEFAULT_VOICE
-from yta_audio_narration.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
-from yta_audio_narration.voice import NarrationVoice
+from yta_audio_narration_common.consts import DEFAULT_VOICE
+from yta_audio_narration_common.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
+from yta_audio_narration_common.voice import NarrationVoice
 from yta_constants.enum import YTAEnum as Enum
 from yta_constants.file import FileType
 from yta_programming.output import Output

{yta_audio_narration-0.0.1 → yta_audio_narration-0.0.2}/src/yta_audio_narration/voices/ttsmp3.py

@@ -9,9 +9,9 @@ characters when using AI. AI is disabled
 by now as the limit makes it not
 interesting for our purpose.
 """
-from yta_audio_narration.consts import DEFAULT_VOICE
-from yta_audio_narration.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
-from yta_audio_narration.voice import NarrationVoice
+from yta_audio_narration_common.consts import DEFAULT_VOICE
+from yta_audio_narration_common.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
+from yta_audio_narration_common.voice import NarrationVoice
 from yta_file_downloader import Downloader
 from yta_constants.file import FileType
 from yta_constants.enum import YTAEnum as Enum

yta_audio_narration-0.0.1/src/yta_audio_narration/__init__.py

@@ -1,3 +0,0 @@
-"""
-Welcome to Youtube Autonomous Audio Narration Module.
-"""

yta_audio_narration-0.0.1/src/yta_audio_narration/consts.py

@@ -1 +0,0 @@
-DEFAULT_VOICE = 'default'

yta_audio_narration-0.0.1/src/yta_audio_narration/enums.py

@@ -1,377 +0,0 @@
-from yta_constants.lang import Language
-from yta_constants.enum import YTAEnum as Enum
-from typing import Union
-
-
-class NarrationLanguage(Enum):
-    """
-    The languages available for voice narrations.
-
-    This list is based on the ISO-639 but not all
-    these languages are available for narrations 
-    and also each narration engine has its own
-    languages available. This list is also manually
-    set in other libraries, so please ensure it
-    keeps updated.
-    """
-
-    DEFAULT = 'default'
-    """
-    This value has been created for those cases
-    in which there is a default language that is
-    being used in the situation we are handling.
-
-    Using this value will provide that default
-    language. For example, a Youtube video can
-    be in Turkish or in English as default,
-    depending on the author. Using this 'default'
-    value will ensure you obtain that Youtube
-    video because that default language will
-    always exist.
-    """
-    ABKHAZIAN = Language.ABKHAZIAN.value
-    AFAR = Language.AFAR.value
-    AFRIKAANS = Language.AFRIKAANS.value
-    AKAN = Language.AKAN.value
-    ALBANIAN = Language.ALBANIAN.value
-    AMHARIC = Language.AMHARIC.value
-    ARABIC = Language.ARABIC.value
-    ARAGONESE = Language.ARAGONESE.value
-    ARMENIAN = Language.ARMENIAN.value
-    ASSAMESE = Language.ASSAMESE.value
-    AVARIC = Language.AVARIC.value
-    AVESTAN = Language.AVESTAN.value
-    AYMARA = Language.AYMARA.value
-    AZERBAIJANI = Language.AZERBAIJANI.value
-    BAMBARA = Language.BAMBARA.value
-    BASHKIR = Language.BASHKIR.value
-    BASQUE = Language.BASQUE.value
-    BELARUSIAN = Language.BELARUSIAN.value
-    BENGALI = Language.BENGALI.value
-    BISLAMA = Language.BISLAMA.value
-    BOSNIAN = Language.BOSNIAN.value
-    BRETON = Language.BRETON.value
-    BULGARIAN = Language.BULGARIAN.value
-    BURMESE = Language.BURMESE.value
-    CATALAN = Language.CATALAN.value
-    CHAMORRO = Language.CHAMORRO.value
-    CHECHEN = Language.CHECHEN.value
-    CHICHEWA = Language.CHICHEWA.value
-    CHINESE = Language.CHINESE.value
-    CHINESE_TRADITIONAL = Language.CHINESE_TRADITIONAL.value
-    # TODO: I think there are more complex values like
-    # this above, but they are not in the list
-    CHURCH_SLAVONIC = Language.CHURCH_SLAVONIC.value
-    CHUVASH = Language.CHUVASH.value
-    CORNISH = Language.CORNISH.value
-    CORSICAN = Language.CORSICAN.value
-    CREE = Language.CREE.value
-    CROATIAN = Language.CROATIAN.value
-    CZECH = Language.CZECH.value
-    DANISH = Language.DANISH.value
-    DIVEHI = Language.DIVEHI.value
-    DUTCH = Language.DUTCH.value
-    DZONGKHA = Language.DZONGKHA.value
-    ENGLISH = Language.ENGLISH.value
-    ESPERANTO = Language.ESPERANTO.value
-    ESTONIAN = Language.ESTONIAN.value
-    EWE = Language.EWE.value
-    FAROESE = Language.FAROESE.value
-    FIJIAN = Language.FIJIAN.value
-    FINNISH = Language.FINNISH.value
-    FRENCH = Language.FRENCH.value
-    WESTERN_FRISIAN = Language.WESTERN_FRISIAN.value
-    FULAH = Language.FULAH.value
-    GAELIC = Language.GAELIC.value
-    GALICIAN = Language.GALICIAN.value
-    GANDA = Language.GANDA.value
-    GEORGIAN = Language.GEORGIAN.value
-    GERMAN = Language.GERMAN.value
-    GREEK = Language.GREEK.value
-    KALAALLISUT = Language.KALAALLISUT.value
-    GUARANI = Language.GUARANI.value
-    GUJARATI = Language.GUJARATI.value
-    HAITIAN = Language.HAITIAN.value
-    HAUSA = Language.HAUSA.value
-    HEBREW = Language.HEBREW.value
-    HERERO = Language.HERERO.value
-    HINDI = Language.HINDI.value
-    HIRI_MOTU = Language.HIRI_MOTU.value
-    HUNGARIAN = Language.HUNGARIAN.value
-    ICELANDIC = Language.ICELANDIC.value
-    IDO = Language.IDO.value
-    IGBO = Language.IGBO.value
-    INDONESIAN = Language.INDONESIAN.value
-    INTERLINGUA = Language.INTERLINGUA.value
-    INTERLINGUE = Language.INTERLINGUE.value
-    INUKTITUT = Language.INUKTITUT.value
-    INUPIAQ = Language.INUPIAQ.value
-    IRISH = Language.IRISH.value
-    ITALIAN = Language.ITALIAN.value
-    JAPANESE = Language.JAPANESE.value
-    JAVANESE = Language.JAVANESE.value
-    KANNADA = Language.KANNADA.value
-    KANURI = Language.KANURI.value
-    KASHMIRI = Language.KASHMIRI.value
-    KAZAKH = Language.KAZAKH.value
-    CENTRAL_KHMER = Language.CENTRAL_KHMER.value
-    KIKUYU = Language.KIKUYU.value
-    KINYARWANDA = Language.KINYARWANDA.value
-    KYRGYZ = Language.KYRGYZ.value
-    KOMI = Language.KOMI.value
-    KONGO = Language.KONGO.value
-    KOREAN = Language.KOREAN.value
-    KUANYAMA = Language.KUANYAMA.value
-    KURDISH = Language.KURDISH.value
-    LAO = Language.LAO.value
-    LATIN = Language.LATIN.value
-    LATVIAN = Language.LATVIAN.value
-    LIMBURGAN = Language.LIMBURGAN.value
-    LINGALA = Language.LINGALA.value
-    LITHUANIAN = Language.LITHUANIAN.value
-    LUBA_KATANGA = Language.LUBA_KATANGA.value
-    LUXEMBOURGISH = Language.LUXEMBOURGISH.value
-    MACEDONIAN = Language.MACEDONIAN.value
-    MALAGASY = Language.MALAGASY.value
-    MALAY = Language.MALAY.value
-    MALAYALAM = Language.MALAYALAM.value
-    MALTESE = Language.MALTESE.value
-    MANX = Language.MANX.value
-    MAORI = Language.MAORI.value
-    MARATHI = Language.MARATHI.value
-    MARSHALLESE = Language.MARSHALLESE.value
-    MONGOLIAN = Language.MONGOLIAN.value
-    NAURU = Language.NAURU.value
-    NAVAJO = Language.NAVAJO.value
-    NORTH_NDEBELE = Language.NORTH_NDEBELE.value
-    SOUTH_NDEBELE = Language.SOUTH_NDEBELE.value
-    NDONGA = Language.NDONGA.value
-    NEPALI = Language.NEPALI.value
-    NORWEGIAN = Language.NORWEGIAN.value
-    NORWEGIAN_BOKMAL = Language.NORWEGIAN_BOKMAL.value
-    NORWEGIAN_NYNORSK = Language.NORWEGIAN_NYNORSK.value
-    OCCITAN = Language.OCCITAN.value
-    OJIBWA = Language.OJIBWA.value
-    ORIYA = Language.ORIYA.value
-    OROMO = Language.OROMO.value
-    OSSETIAN = Language.OSSETIAN.value
-    PALI = Language.PALI.value
-    PASHTO = Language.PASHTO.value
-    PERSIAN = Language.PERSIAN.value
-    POLISH = Language.POLISH.value
-    PORTUGUESE = Language.PORTUGUESE.value
-    PUNJABI = Language.PUNJABI.value
-    QUECHUA = Language.QUECHUA.value
-    ROMANIAN = Language.ROMANIAN.value
-    ROMANSH = Language.ROMANSH.value
-    RUNDI = Language.RUNDI.value
-    RUSSIAN = Language.RUSSIAN.value
-    NORTHERN_SAMI = Language.NORTHERN_SAMI.value
-    SAMOAN = Language.SAMOAN.value
-    SANGO = Language.SANGO.value
-    SANSKRIT = Language.SANSKRIT.value
-    SARDINIAN = Language.SARDINIAN.value
-    SERBIAN = Language.SERBIAN.value
-    SHONA = Language.SHONA.value
-    SINDHI = Language.SINDHI.value
-    SINHALA = Language.SINHALA.value
-    SLOVAK = Language.SLOVAK.value
-    SLOVENIAN = Language.SLOVENIAN.value
-    SOMALI = Language.SOMALI.value
-    SOUTHERN_SOTHO = Language.SOUTHERN_SOTHO.value
-    SPANISH = Language.SPANISH.value
-    SUNDANESE = Language.SUNDANESE.value
-    SWAHILI = Language.SWAHILI.value
-    SWATI = Language.SWATI.value
-    SWEDISH = Language.SWEDISH.value
-    TAGALOG = Language.TAGALOG.value
-    TAHITIAN = Language.TAHITIAN.value
-    TAJIK = Language.TAJIK.value
-    TAMIL = Language.TAMIL.value
-    TATAR = Language.TATAR.value
-    TELUGU = Language.TELUGU.value
-    THAI = Language.THAI.value
-    TIBETAN = Language.TIBETAN.value
-    TIGRINYA = Language.TIGRINYA.value
-    TONGA = Language.TONGA.value
-    TSONGA = Language.TSONGA.value
-    TSWANA = Language.TSWANA.value
-    TURKISH = Language.TURKISH.value
-    TURKMEN = Language.TURKMEN.value
-    TWI = Language.TWI.value
-    UIGHUR = Language.UIGHUR.value
-    UKRAINIAN = Language.UKRAINIAN.value
-    URDU = Language.URDU.value
-    UZBEK = Language.UZBEK.value
-    VENDA = Language.VENDA.value
-    VIETNAMESE = Language.VIETNAMESE.value
-    VOLAPUK = Language.VOLAPUK.value
-    WALLOON = Language.WALLOON.value
-    WELSH = Language.WELSH.value
-    WOLOF = Language.WOLOF.value
-    XHOSA = Language.XHOSA.value
-    SICHUAN_YI = Language.SICHUAN_YI.value
-    YIDDISH = Language.YIDDISH.value
-    YORUBA = Language.YORUBA.value
-    ZHUANG = Language.ZHUANG.value
-    ZULU = Language.ZULU.value
-
-# Engine > Language > NarratorName > Speed | Emotion
-   
-class VoiceEmotion(Enum):
-    """
-    The emotion to be transmited in the voice
-    narration.
-    """
-
-    DEFAULT = 'default'
-    SAD = 'sad'
-    NORMAL = 'normal'
-    HAPPY = 'happy'
-    # TODO: Add more when available
-
-class VoiceSpeed(Enum):
-    """
-    The speed to be used within the voice narration.
-    """
-
-    DEFAULT = 'default'
-    SLOW = 'slow'
-    NORMAL = 'normal'
-    FAST = 'fast'
-    # TODO: Add more when available
-
-class VoicePitch(Enum):
-    """
-    The pitch to be used within the voice narration.
-    """
-
-    DEFAULT = 'default'
-    LOW = 'low'
-    NORMAL = 'normal'
-    HIGH = 'high'
-    # TODO: Add more when available
-
-class VoiceNarrationEngine(Enum):
-    """
-    The engines we have available for voice narration
-    generation.
-    """
-
-    DEFAULT = 'default'
-    """
-    When this option is provided, the system will
-    choose one of the available enum elements.
-    """
-    COQUI = 'coqui'
-    GOOGLE = 'google'
-    MICROSOFT = 'microsoft'
-    OPEN_VOICE = 'open_voice'
-    TETYYS = 'tetyys'
-    TIKTOK = 'tiktok'
-    TORTOISE = 'tortoise'
-    TTSMP3 = 'ttsmp3'
-
-    def _get_engine(
-        self
-    ) -> 'VoiceNarrationEngine':
-        """
-        We turn the DEFAULT instance into a specific
-        one to simplify the way we handle the options.
-
-        For internal use only.
-        """
-        return (
-            VoiceNarrationEngine.GOOGLE
-            if self is VoiceNarrationEngine.DEFAULT else
-            self
-        )
-
-    def get_voice_narrator_class(
-        self
-    # ) -> Union['CoquiVoiceNarrator', 'GoogleVoiceNarrator', 'MicrosoftVoiceNarrator', 'OpenVoiceVoiceNarrator', 'TetyysVoiceNarrator', 'TiktokVoiceNarrator', 'TortoiseVoiceNarrator', 'Ttsmp3VoiceNarrator']:
-    ) -> Union['CoquiVoiceNarrator', 'GoogleVoiceNarrator', 'MicrosoftVoiceNarrator', 'TetyysVoiceNarrator', 'TiktokVoiceNarrator', 'TortoiseVoiceNarrator', 'Ttsmp3VoiceNarrator']:
-        """
-        Get the VoiceNarrator class associated with this
-        enum instance.
-        """
-        # from yta_audio.voice.generation.narrator import CoquiVoiceNarrator, GoogleVoiceNarrator, MicrosoftVoiceNarrator, OpenVoiceVoiceNarrator, TetyysVoiceNarrator, TiktokVoiceNarrator, TortoiseVoiceNarrator, Ttsmp3VoiceNarrator
-        from yta_audio.voice.generation.narrator import CoquiVoiceNarrator, GoogleVoiceNarrator, MicrosoftVoiceNarrator, TetyysVoiceNarrator, TiktokVoiceNarrator, TortoiseVoiceNarrator, Ttsmp3VoiceNarrator
-
-        engine = self._get_engine()
-
-        return {
-            VoiceNarrationEngine.GOOGLE: GoogleVoiceNarrator,
-            VoiceNarrationEngine.COQUI: CoquiVoiceNarrator,
-            VoiceNarrationEngine.MICROSOFT: MicrosoftVoiceNarrator,
-            # VoiceNarrationEngine.OPEN_VOICE: OpenVoiceVoiceNarrator,
-            VoiceNarrationEngine.TETYYS: TetyysVoiceNarrator,
-            VoiceNarrationEngine.TIKTOK: TiktokVoiceNarrator,
-            VoiceNarrationEngine.TORTOISE: TortoiseVoiceNarrator,
-            VoiceNarrationEngine.TTSMP3: Ttsmp3VoiceNarrator,
-        }[engine]
-    
-    @property
-    def available_languages(
-        self
-    ) -> list[NarrationLanguage]:
-        return self.get_voice_narrator_class().get_available_languages()
-    
-    def is_language_valid(
-        self,
-        language: NarrationLanguage
-    ) -> bool:
-        """
-        Check if the given 'language' is accepted by
-        this engine.
-        """
-        return NarrationLanguage.to_enum(language) in self.available_languages
-    
-    def get_available_narrator_names(
-        self,
-        language: NarrationLanguage
-    ) -> list[str]:
-        return self.get_voice_narrator_class().get_available_narrator_names(language)
-    
-    def is_narrator_name_valid(
-        self,
-        language: NarrationLanguage,
-        narration_name: str
-    ) -> bool:
-        return narration_name in self.get_available_narrator_names(language)
-
-    @property
-    def available_emotions(
-        self
-    ) -> list[VoiceEmotion]:
-        return self.get_voice_narrator_class().get_available_emotions()
-    
-    def is_emotion_valid(
-        self,
-        emotion: VoiceEmotion
-    ) -> bool:
-        return VoiceEmotion.to_enum(emotion) in self.available_emotions
-
-    @property
-    def available_speeds(
-        self
-    ) -> list[VoiceSpeed]:
-        return self.get_voice_narrator_class().get_available_speeds()
-    
-    def is_speed_valid(
-        self,
-        speed: VoiceSpeed
-    ) -> bool:
-        return VoiceSpeed.to_enum(speed) in self.available_speeds
-    
-    @property
-    def available_pitches(
-        self
-    ) -> list[VoicePitch]:
-        return self.get_voice_narrator_class().get_available_pitches()
-    
-    def is_pitch_valid(
-        self,
-        pitch: VoicePitch
-    ) -> bool:
-        return VoicePitch.to_enum(pitch) in self.available_pitches

yta_audio_narration-0.0.1/src/yta_audio_narration/voice.py

@@ -1,88 +0,0 @@
-from yta_audio_narration.enums import NarrationLanguage, VoiceSpeed, VoiceEmotion, VoicePitch
-from dataclasses import dataclass
-from abc import abstractmethod
-
-
-@dataclass
-class NarrationVoice:
-    """
-    Dataclass to be implemented by other custom
-    dataclasses that will determine the narration
-    voice parameters of our voice narration 
-    engines.
-    """
-
-    name: str
-    """
-    The voice narration name.
-    """
-    emotion: VoiceEmotion
-    """
-    The voice narration emotion.
-    """
-    speed: VoiceSpeed
-    """
-    The voice narration desired speed.
-    """
-    pitch : VoicePitch
-    """
-    The voice narration desired pitch.
-    """
-    language: NarrationLanguage
-    """
-    The language to be used with the voice narration.
-    """
-    # TODO: Maybe add something more like
-    # pitch or something
-
-    def __init__(
-        self,
-        name: str = '',
-        emotion: VoiceEmotion = VoiceEmotion.DEFAULT,
-        speed: VoiceSpeed = VoiceSpeed.DEFAULT,
-        pitch: VoicePitch = VoicePitch.DEFAULT,
-        language: NarrationLanguage = NarrationLanguage.DEFAULT
-    ):
-        self.validate(name, emotion, speed, pitch, language)
-
-        # TODO: Maybe we could receive an Enum name 
-        # and we need to parse it
-        self.name = name
-        self.emotion = VoiceEmotion.to_enum(emotion)
-        self.speed = VoiceSpeed.to_enum(speed)
-        self.pitch = VoicePitch.to_enum(pitch)
-        self.language = NarrationLanguage.to_enum(language)
-
-    @abstractmethod
-    def validate(
-        self,
-        name: str,
-        emotion: VoiceEmotion,
-        speed: VoiceSpeed,
-        pitch: VoicePitch,
-        language: NarrationLanguage
-    ):
-        """
-        Check if the parameters provided are valid or not
-        and raise an Exception if not.
-
-        This method can also process the attributes to make
-        some modifications and return them to be stored
-        once they have been modified.
-
-        This method must be overwritten.
-        """
-        pass
-
-    @staticmethod
-    @abstractmethod
-    def default():
-        """
-        Return an instance of your Narration Voice custom
-        class with the default values for that type of 
-        class.
-
-        This method must be overwritten.
-        """
-        pass
-

yta_audio_narration-0.0.1/src/yta_audio_narration/voices/coqui.py

@@ -1,278 +0,0 @@
-"""
-You can see anything you need here:
-- https://docs.coqui.ai/en/latest/
-
-As this is the first voice generator engine,
-I will explain some things here that are
-important for all the voice narrator engines
-that we are creating.
-
-We have options, and we will have all the 
-array options fulfilled with, at least, a
-NORMAL and a DEFAULT options. This, even if
-the voice narrator engine doesn't use those
-options, will be handled. Then, when 
-generating the voice narration, it will be
-ignored by our system.
-
--- Update 19/04/2025 --
-I've found that they created a fork in
-https://github.com/idiap/coqui-ai-TTS with
-a new version that is maintained, and the 
-'tts' was generating conflicts.
-"""
-from yta_audio_narration.consts import DEFAULT_VOICE
-from yta_audio_narration.enums import NarrationLanguage, VoiceEmotion, VoiceSpeed, VoicePitch
-from yta_audio_narration.voice import NarrationVoice
-from yta_constants.enum import YTAEnum as Enum
-from yta_constants.file import FileType
-from yta_programming.output import Output
-from typing import Union
-from TTS.api import TTS
-
-
-"""
-The options below are specified even if we
-don't use them later when processing the 
-voice narration. This is to keep the same
-structure for any voice narration and to
-simplify the way we offer the options in
-an API that is able to make requests.
-"""
-
-# 1. The voices we accept, as Enums
-class CoquiVoiceName(Enum):
-    """
-    Available voices. The value is what is used
-    for the audio creation.
-    """
-
-    # tts_es_fastpitch_multispeaker.nemo
-    # These below are the 2 Spanish models that exist
-    DEFAULT = DEFAULT_VOICE
-    SPANISH_MODEL_A = 'tts_models/es/mai/tacotron2-DDC'
-    SPANISH_MODEL_B = 'tts_models/es/css10/vits'
-    # TODO: There are more voices
-
-# 2. The languages we accept
-LANGUAGE_OPTIONS = [
-    NarrationLanguage.DEFAULT,
-    NarrationLanguage.SPANISH
-]
-
-# 3. The emotions we accept
-EMOTION_OPTIONS = [
-    VoiceEmotion.DEFAULT,
-    VoiceEmotion.NORMAL,
-]
-
-# 4. The speeds we accept
-SPEED_OPTIONS = [
-    VoiceSpeed.DEFAULT,
-    VoiceSpeed.NORMAL,
-]
-
-# 5. The pitches we accept
-PITCH_OPTIONS = [
-    VoicePitch.DEFAULT,
-    VoicePitch.NORMAL,
-]
-
-class CoquiNarrationVoice(NarrationVoice):
-    """
-    Voice instance to be used when narrating with
-    Coqui engine.
-    """
-
-    @property
-    def processed_name(
-        self
-    ) -> str:
-        """
-        Get the usable name value from the one that has
-        been set when instantiating the instance.
-        """
-        return (
-            CoquiVoiceName.SPANISH_MODEL_A.value
-            if CoquiVoiceName.to_enum(self.name) == CoquiVoiceName.DEFAULT else
-            CoquiVoiceName.to_enum(self.name).value
-        )
-
-    @property
-    def processed_emotion(
-        self
-    ) -> str:
-        """
-        Get the usable emotion value from the one that
-        has been set when instantiating the instance.
-        """
-        # This narration is not able to handle any 
-        # emotion (at least by now)
-        return None
-    
-    @property
-    def processed_speed(
-        self
-    ) -> float:
-        """
-        Get the usable speed value from the one that
-        has been set when instantiating the instance.
-        """
-        # By now we are not handling the speed with
-        # this voice
-        return 1.0
-
-    @property
-    def processed_pitch(
-        self
-    ) -> float:
-        """
-        Get the usable pitch value from the one that
-        has been set when instantiating the instance.
-        """
-        # By now we are not handling the pitch with
-        # this voice
-        return None
-    
-    @property
-    def processed_language(
-        self
-    ) -> str:
-        """
-        Get the usable language value from the one that
-        has been set when instantiating the instance.
-        """
-        return self.language.value
-
-    def validate(
-        self,
-        name: str,
-        emotion: VoiceEmotion,
-        speed: VoiceSpeed,
-        pitch: VoicePitch,
-        language: NarrationLanguage
-    ):
-        CoquiVoiceName.to_enum(name)
-        if VoiceEmotion.to_enum(emotion) not in EMOTION_OPTIONS:
-            raise Exception(f'The provided {emotion} is not valid for this narration voice.')
-        if VoiceSpeed.to_enum(speed) not in SPEED_OPTIONS:
-            raise Exception(f'The provided {speed} is not valid for this narration voice.')
-        if VoicePitch.to_enum(pitch) not in PITCH_OPTIONS:
-            raise Exception(f'The provided {pitch} is not valid for this narration voice.')
-        if NarrationLanguage.to_enum(language) not in LANGUAGE_OPTIONS:
-            raise Exception(f'The provided {language} is not valid for this narration voice.')
-        
-    @staticmethod
-    def default():
-        return CoquiNarrationVoice(
-            name = CoquiVoiceName.DEFAULT.value, 
-            emotion = VoiceEmotion.DEFAULT,
-            speed = VoiceSpeed.DEFAULT,
-            pitch = VoicePitch.DEFAULT,
-            language = NarrationLanguage.DEFAULT
-        )
-
-# The voices but for a specific language, to be able to
-# choose one when this is requested from the outside
-def get_narrator_names_by_language(
-    language: NarrationLanguage
-) -> list[str]:
-    """
-    Get the voices that are available for the
-    given 'language'.
-    """
-    language = NarrationLanguage.to_enum(language)
-    language = (
-        NarrationLanguage.SPANISH
-        if language is NarrationLanguage.DEFAULT else
-        language
-    )
-
-    return {
-        NarrationLanguage.SPANISH: [
-            CoquiVoiceName.DEFAULT.value,
-            CoquiVoiceName.SPANISH_MODEL_A.value,
-            CoquiVoiceName.SPANISH_MODEL_B.value
-        ]
-    }[language]
-
-
-# All the remaining functionality we need to make it
-# work properly
-def narrate(
-    text: str,
-    voice: CoquiNarrationVoice = CoquiNarrationVoice.default(),
-    output_filename: Union[str, None] = None
-) -> str:
-    """
-    Generates a narration audio file with the provided 'text' that
-    will be stored as 'output_filename' file.
-
-    This method uses a Spanish model so 'text' must be in Spanish.
-
-    This method will take some time to generate the narration.
-    """
-    output_filename = Output.get_filename(output_filename, FileType.AUDIO)
-
-    TTS(
-        model_name = voice.processed_name
-    ).tts_to_file(
-        # TODO: Implement 'emotion', 'speed', etc. when known
-        # how they work, the accepted values, etc. By now I'm
-        # using the properties but with the default values
-        text = text,
-        speaker = None,
-        language = None,
-        emotion = voice.processed_emotion,
-        speed = voice.processed_speed,
-        file_path = output_filename
-    )
-    
-    # TODO: This was in the previous version, remove when the
-    # above is working.
-    # tts = TTS(model_name = voice.name)
-    # # There is 'language', 'emotion', 'speed'...
-    # tts.tts_to_file(text = text, file_path = output_filename)
-
-    return output_filename
-
-def narrate_imitating_voice(
-    text: str,
-    input_filename: str,
-    output_filename: Union[str, None] = None
-):
-    """
-    Narrates the provided 'text' by imitating the provided 'input_filename'
-    audio file (that must be a voice narrating something) and saves the 
-    narration as 'output_filename'.
-
-    The 'input_filename' could be an array of audio filenames.
-
-    Language is set 'es' in code by default.
-
-    This method will take time as it will recreate the voice parameters with
-    which the narration will be created after that.
-
-    ANNOTATIONS: This method is only copying the way the narration voice 
-    talks, but not the own voice. This is not working as expected, as we are
-    not cloning voices, we are just imitating the tone. We need another way
-    to actually clone the voice as Elevenlabs do.
-    """
-    # TODO: This is not validating if audio file...
-    if not input_filename:
-        raise Exception('No "input_filename" provided.')
-    
-    output_filename = Output.get_filename(output_filename, FileType.AUDIO)
-
-    tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2")
-    # This below will use the latest XTTS_v2 (needs to download the model)
-    #tts = TTS('xtts')
-
-    # TODO: Implement a way of identifying and storing the voices we create to
-    # be able to use again them without recreating them twice.
-
-    # input_filename can be an array of wav files
-    # generate speech by cloning a voice using default settings
-    tts.tts_to_file(text = text, file_path = output_filename, speaker_wav = input_filename, language = 'es')
-
-    return output_filename