webscout 6.4__py3-none-any.whl → 6.6__py3-none-any.whl

webscout/Provider/TTS/deepgram.py

@@ -0,0 +1,183 @@
+import time
+import requests
+import pathlib
+import base64
+from io import BytesIO
+from playsound import playsound
+from webscout import exceptions
+from webscout.AIbase import TTSProvider
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from webscout.Litlogger import LitLogger, LogFormat, ColorScheme
+from webscout.litagent import LitAgent
+from . import utils
+
+class DeepgramTTS(TTSProvider): 
+    """
+    Text-to-speech provider using the DeepgramTTS API.
+    """
+    # Request headers
+    headers: dict[str, str] = {
+        "User-Agent": LitAgent().random()
+    }
+    cache_dir = pathlib.Path("./audio_cache")
+    all_voices: dict[str, str] = {
+        "Asteria": "aura-asteria-en", "Arcas": "aura-arcas-en", "Luna": "aura-luna-en",
+        "Zeus": "aura-zeus-en", "Orpheus": "aura-orpheus-en", "Angus": "aura-angus-en",
+        "Athena": "aura-athena-en", "Helios": "aura-helios-en", "Hera": "aura-hera-en",
+        "Orion": "aura-orion-en", "Perseus": "aura-perseus-en", "Stella": "aura-stella-en"
+    }
+
+    def __init__(self, timeout: int = 20, proxies: dict = None):
+        """Initializes the DeepgramTTS TTS client."""
+        self.session = requests.Session()
+        self.session.headers.update(self.headers)
+        if proxies:
+            self.session.proxies.update(proxies)
+        self.timeout = timeout
+        self.logger = LitLogger(
+            name="DeepgramTTS",
+            format=LogFormat.MODERN_EMOJI,
+            color_scheme=ColorScheme.AURORA
+        )
+
+    def tts(self, text: str, voice: str = "Brian", verbose: bool = True) -> str:
+        """
+        Converts text to speech using the DeepgramTTS API and saves it to a file.
+
+        Args:
+            text (str): The text to convert to speech
+            voice (str): The voice to use for TTS (default: "Brian")
+            verbose (bool): Whether to print progress messages (default: True)
+
+        Returns:
+            str: Path to the generated audio file
+
+        Raises:
+            AssertionError: If the specified voice is not available
+            requests.RequestException: If there's an error communicating with the API
+            RuntimeError: If there's an error processing the audio
+        """
+        assert (
+            voice in self.all_voices
+        ), f"Voice '{voice}' not one of [{', '.join(self.all_voices.keys())}]"
+
+        url = "https://deepgram.com/api/ttsAudioGeneration"
+        filename = self.cache_dir / f"{int(time.time())}.mp3"  
+
+        # Split text into sentences using the utils module
+        sentences = utils.split_sentences(text)
+        if verbose:
+            for index, sen in enumerate(sentences):
+                self.logger.debug(f"Sentence {index}: {sen}")
+
+        def generate_audio_for_chunk(part_text: str, part_number: int):
+            """
+            Generate audio for a single chunk of text.
+
+            Args:
+                part_text (str): The text chunk to convert
+                part_number (int): The chunk number for ordering
+
+            Returns:
+                tuple: (part_number, audio_data)
+
+            Raises:
+                requests.RequestException: If there's an API error
+            """
+            max_retries = 3
+            retry_count = 0
+            
+            while retry_count < max_retries:
+                try:
+                    payload = {"text": part_text, "model": self.all_voices[voice]}
+                    response = self.session.post(
+                        url=url, 
+                        headers=self.headers, 
+                        json=payload, 
+                        stream=True, 
+                        timeout=self.timeout
+                    )
+                    response.raise_for_status()
+
+                    response_data = response.json().get('data')
+                    if response_data:
+                        audio_data = base64.b64decode(response_data)
+                        if verbose:
+                            self.logger.success(f"Chunk {part_number} processed successfully 🎉")
+                        return part_number, audio_data
+                    
+                    if verbose:
+                        self.logger.warning(f"No data received for chunk {part_number}. Attempt {retry_count + 1}/{max_retries} ⚠️")
+                    
+                except requests.RequestException as e:
+                    if verbose:
+                        self.logger.error(f"Error processing chunk {part_number}: {str(e)}. Attempt {retry_count + 1}/{max_retries} 🚨")
+                    if retry_count == max_retries - 1:
+                        raise
+                
+                retry_count += 1
+                time.sleep(1)
+            
+            raise RuntimeError(f"Failed to generate audio for chunk {part_number} after {max_retries} attempts")
+
+        try:
+            # Create the audio_cache directory if it doesn't exist
+            self.cache_dir.mkdir(parents=True, exist_ok=True)
+
+            # Using ThreadPoolExecutor to handle requests concurrently
+            with ThreadPoolExecutor() as executor:
+                futures = {
+                    executor.submit(generate_audio_for_chunk, sentence.strip(), chunk_num): chunk_num 
+                    for chunk_num, sentence in enumerate(sentences, start=1)
+                }
+                
+                # Dictionary to store results with order preserved
+                audio_chunks = {}
+
+                for future in as_completed(futures):
+                    chunk_num = futures[future]
+                    try:
+                        part_number, audio_data = future.result()
+                        audio_chunks[part_number] = audio_data
+                    except Exception as e:
+                        raise RuntimeError(f"Failed to generate audio for chunk {chunk_num}: {str(e)}")
+
+                # Combine all audio chunks in order
+                with open(filename, 'wb') as f:
+                    for chunk_num in sorted(audio_chunks.keys()):
+                        f.write(audio_chunks[chunk_num])
+
+                if verbose:
+                    self.logger.success(f"Audio saved to {filename} 🎉")
+                return str(filename)
+
+        except Exception as e:
+            self.logger.critical(f"Failed to generate audio: {str(e)} 🚨")
+            raise RuntimeError(f"Failed to generate audio: {str(e)}")
+
+    def play_audio(self, filename: str):
+        """
+        Plays an audio file using playsound.
+
+        Args:
+            filename (str): The path to the audio file.
+
+        Raises:
+            RuntimeError: If there is an error playing the audio.
+        """
+        try:
+            playsound(filename)
+        except Exception as e:
+            self.logger.error(f"Failed to play audio: {str(e)} 🚨")
+            raise RuntimeError(f"Failed to play audio: {str(e)}")
+
+# Example usage
+if __name__ == "__main__":
+    deepgram = DeepgramTTS()
+    text = "This is a test of the DeepgramTTS text-to-speech API. It supports multiple sentences. Let's see how it works!"
+
+    deepgram.logger.info("Generating audio...")
+    audio_file = deepgram.tts(text, voice="Brian") 
+
+    deepgram.logger.info("Playing audio...")
+    deepgram.play_audio(audio_file)

webscout/Provider/TTS/elevenlabs.py

@@ -0,0 +1,137 @@
+import time
+import requests
+import pathlib
+from io import BytesIO
+from playsound import playsound
+from webscout import exceptions
+from webscout.AIbase import TTSProvider
+from webscout.Litlogger import LitLogger, LogFormat, ColorScheme
+from webscout.litagent import LitAgent
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from . import utils
+
+class ElevenlabsTTS(TTSProvider): 
+    """
+    Text-to-speech provider using the ElevenlabsTTS API.
+    """
+    # Request headers
+    headers: dict[str, str] = {
+        "User-Agent": LitAgent().random()
+    }
+    cache_dir = pathlib.Path("./audio_cache")
+    all_voices: dict[str, str] = {"Brian": "nPczCjzI2devNBz1zQrb", "Alice":"Xb7hH8MSUJpSbSDYk0k2", "Bill":"pqHfZKP75CvOlQylNhV4", "Callum":"N2lVS1w4EtoT3dr4eOWO", "Charlie":"IKne3meq5aSn9XLyUdCD", "Charlotte":"XB0fDUnXU5powFXDhCwa", "Chris":"iP95p4xoKVk53GoZ742B", "Daniel":"onwK4e9ZLuTAKqWW03F9", "Eric":"cjVigY5qzO86Huf0OWal", "George":"JBFqnCBsd6RMkjVDRZzb", "Jessica":"cgSgspJ2msm6clMCkdW9", "Laura":"FGY2WhTYpPnrIDTdsKH5", "Liam":"TX3LPaxmHKxFdv7VOQHJ", "Lily":"pFZP5JQG7iQjIQuC4Bku", "Matilda":"XrExE9yKIg1WjnnlVkGX", "Sarah":"EXAVITQu4vr4xnSDxMaL", "Will":"bIHbv24MWmeRgasZH58o"}
+
+    def __init__(self, timeout: int = 20, proxies: dict = None):
+        """Initializes the ElevenlabsTTS TTS client."""
+        self.session = requests.Session()
+        self.session.headers.update(self.headers)
+        if proxies:
+            self.session.proxies.update(proxies)
+        self.timeout = timeout
+        self.params = {'allow_unauthenticated': '1'}
+        self.logger = LitLogger(
+            name="ElevenlabsTTS",
+            format=LogFormat.MODERN_EMOJI,
+            color_scheme=ColorScheme.AURORA
+        )
+
+    def tts(self, text: str, voice: str = "Brian", verbose:bool = True) -> str:
+        """
+        Converts text to speech using the ElevenlabsTTS API and saves it to a file.
+        """
+        assert (
+            voice in self.all_voices
+        ), f"Voice '{voice}' not one of [{', '.join(self.all_voices.keys())}]"
+
+        filename = self.cache_dir / f"{int(time.time())}.mp3"  
+
+        # Split text into sentences
+        sentences = utils.split_sentences(text)
+
+        # Function to request audio for each chunk
+        def generate_audio_for_chunk(part_text: str, part_number: int):
+            while True:
+                try:
+                    json_data = {'text': part_text, 'model_id': 'eleven_multilingual_v2'}
+                    response = self.session.post(f'https://api.elevenlabs.io/v1/text-to-speech/{self.all_voices[voice]}',params=self.params, headers=self.headers, json=json_data, timeout=self.timeout)
+                    response.raise_for_status()
+
+                    # Create the audio_cache directory if it doesn't exist
+                    self.cache_dir.mkdir(parents=True, exist_ok=True) 
+
+                    # Check if the request was successful
+                    if response.ok and response.status_code == 200:
+                        if verbose:
+                            self.logger.success(f"Chunk {part_number} processed successfully 🎉")
+                        return part_number, response.content
+                    else:
+                        if verbose:
+                            self.logger.warning(f"No data received for chunk {part_number}. Retrying...")
+                except requests.RequestException as e:
+                    if verbose:
+                        self.logger.error(f"Error for chunk {part_number}: {e}. Retrying... 🔄")
+                    time.sleep(1)
+        try:
+            # Using ThreadPoolExecutor to handle requests concurrently
+            with ThreadPoolExecutor() as executor:
+                futures = {executor.submit(generate_audio_for_chunk, sentence.strip(), chunk_num): chunk_num 
+                        for chunk_num, sentence in enumerate(sentences, start=1)}
+                
+                # Dictionary to store results with order preserved
+                audio_chunks = {}
+
+                for future in as_completed(futures):
+                    chunk_num = futures[future]
+                    try:
+                        part_number, audio_data = future.result()
+                        audio_chunks[part_number] = audio_data  # Store the audio data in correct sequence
+                    except Exception as e:
+                        if verbose:
+                            self.logger.error(f"Failed to generate audio for chunk {chunk_num}: {e} 🚨")
+
+            # Combine audio chunks in the correct sequence
+            combined_audio = BytesIO()
+            for part_number in sorted(audio_chunks.keys()):
+                combined_audio.write(audio_chunks[part_number])
+                if verbose:
+                    self.logger.debug(f"Added chunk {part_number} to the combined file.")
+
+            # Save the combined audio data to a single file
+            with open(filename, 'wb') as f:
+                f.write(combined_audio.getvalue())
+            if verbose:
+                self.logger.info(f"Final Audio Saved as {filename} 🔊")
+            return filename.as_posix()
+
+        except requests.exceptions.RequestException as e:
+            self.logger.critical(f"Failed to perform the operation: {e} 🚨")
+            raise exceptions.FailedToGenerateResponseError(
+                f"Failed to perform the operation: {e}"
+            )
+        
+    def play_audio(self, filename: str):
+        """
+        Plays an audio file using playsound.
+
+        Args:
+            filename (str): The path to the audio file.
+
+        Raises:
+            RuntimeError: If there is an error playing the audio.
+        """
+        try:
+            playsound(filename)
+        except Exception as e:
+            self.logger.error(f"Error playing audio: {e} 🔇")
+            raise RuntimeError(f"Error playing audio: {e}")
+
+# Example usage
+if __name__ == "__main__":
+    elevenlabs = ElevenlabsTTS()
+    text = "This is a test of the ElevenlabsTTS text-to-speech API. It supports multiple sentences and advanced logging."
+
+    elevenlabs.logger.info("Generating audio...")
+    audio_file = elevenlabs.tts(text, voice="Brian") 
+
+    elevenlabs.logger.info("Playing audio...")
+    elevenlabs.play_audio(audio_file)

webscout/Provider/TTS/gesserit.py

@@ -0,0 +1,151 @@
+import time
+import requests
+import pathlib
+import base64
+from io import BytesIO
+from playsound import playsound
+from webscout import exceptions
+from webscout.AIbase import TTSProvider
+from webscout.Litlogger import LitLogger, LogFormat, ColorScheme
+from webscout.litagent import LitAgent
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from . import utils
+
+class GesseritTTS(TTSProvider): 
+    """Text-to-speech provider using the GesseritTTS API."""
+    # Request headers
+    headers: dict[str, str] = {
+        "User-Agent": LitAgent().random()
+    }
+    cache_dir = pathlib.Path("./audio_cache")
+    all_voices: dict[str, str] = {
+        "Emma": "en_us_001",  # Female Voice
+        "Liam": "en_us_006",  # Male Voice
+        "Noah": "en_us_007",  # Male Voice
+        "Oliver": "en_us_009",  # Male Voice
+        "Elijah": "en_us_010",  # Male Voice
+        "James": "en_male_narration",  # Male Voice
+        "Charlie": "en_male_funny",  # Male Voice
+        "Sophia": "en_female_emotional",  # Female Voice
+        "Cody": "en_male_cody",  # Male Voice
+    }
+
+    def __init__(self, timeout: int = 20, proxies: dict = None):
+        """Initializes the GesseritTTS TTS client."""
+        self.session = requests.Session()
+        self.session.headers.update(self.headers)
+        if proxies:
+            self.session.proxies.update(proxies)
+        self.timeout = timeout
+        self.logger = LitLogger(
+            name="GesseritTTS",
+            format=LogFormat.MODERN_EMOJI,
+            color_scheme=ColorScheme.AURORA
+        )
+
+    def tts(self, text: str, voice: str = "Oliver", verbose:bool = True) -> str:
+        """Converts text to speech using the GesseritTTS API and saves it to a file."""
+        assert (
+            voice in self.all_voices
+        ), f"Voice '{voice}' not one of [{', '.join(self.all_voices.keys())}]"
+
+        filename = self.cache_dir / f"{int(time.time())}.mp3"
+
+        voice_id = self.all_voices[voice]
+
+        # Split text into sentences
+        sentences = utils.split_sentences(text)
+
+        # Function to request audio for each chunk
+        def generate_audio_for_chunk(part_text: str, part_number: int):
+            while True:
+                try:
+                    payload = {
+                        "text": part_text,
+                        "voice": voice_id
+                    }
+                    response = self.session.post('https://gesserit.co/api/tiktok-tts', headers=self.headers, json=payload, timeout=self.timeout)
+                    response.raise_for_status()
+
+                    # Create the audio_cache directory if it doesn't exist
+                    self.cache_dir.mkdir(parents=True, exist_ok=True) 
+
+                    # Check if the request was successful
+                    if response.ok and response.status_code == 200:
+                        data = response.json()
+                        audio_base64 = data["audioUrl"].split(",")[1]
+                        audio_data = base64.b64decode(audio_base64)
+                        if verbose:
+                            self.logger.success(f"Chunk {part_number} processed successfully 🎉")
+                        return part_number, audio_data
+                    else:
+                        if verbose:
+                            self.logger.warning(f"No data received for chunk {part_number}. Retrying...")
+                except requests.RequestException as e:
+                    if verbose:
+                        self.logger.error(f"Error for chunk {part_number}: {e}. Retrying... 🔄")
+                    time.sleep(1)
+        try:
+            # Using ThreadPoolExecutor to handle requests concurrently
+            with ThreadPoolExecutor() as executor:
+                futures = {executor.submit(generate_audio_for_chunk, sentence.strip(), chunk_num): chunk_num 
+                        for chunk_num, sentence in enumerate(sentences, start=1)}
+                
+                # Dictionary to store results with order preserved
+                audio_chunks = {}
+
+                for future in as_completed(futures):
+                    chunk_num = futures[future]
+                    try:
+                        part_number, audio_data = future.result()
+                        audio_chunks[part_number] = audio_data  # Store the audio data in correct sequence
+                    except Exception as e:
+                        if verbose:
+                            self.logger.error(f"Failed to generate audio for chunk {chunk_num}: {e} 🚨")
+
+            # Combine audio chunks in the correct sequence
+            combined_audio = BytesIO()
+            for part_number in sorted(audio_chunks.keys()):
+                combined_audio.write(audio_chunks[part_number])
+                if verbose:
+                    self.logger.debug(f"Added chunk {part_number} to the combined file.")
+
+            # Save the combined audio data to a single file
+            with open(filename, 'wb') as f:
+                f.write(combined_audio.getvalue())
+            if verbose:
+                self.logger.info(f"Final Audio Saved as {filename} 🔊")
+            return filename.as_posix()
+
+        except requests.exceptions.RequestException as e:
+            self.logger.critical(f"Failed to perform the operation: {e} 🚨")
+            raise exceptions.FailedToGenerateResponseError(
+                f"Failed to perform the operation: {e}"
+            )
+        
+    def play_audio(self, filename: str):
+        """
+        Plays an audio file using playsound.
+
+        Args:
+            filename (str): The path to the audio file.
+
+        Raises:
+            RuntimeError: If there is an error playing the audio.
+        """
+        try:
+            playsound(filename)
+        except Exception as e:
+            self.logger.error(f"Error playing audio: {e} 🔇")
+            raise RuntimeError(f"Error playing audio: {e}")
+
+# Example usage
+if __name__ == "__main__":
+    gesserit = GesseritTTS()
+    text = "This is a test of the GesseritTTS text-to-speech API. It supports multiple sentences and advanced logging."
+
+    gesserit.logger.info("Generating audio...")
+    audio_file = gesserit.tts(text, voice="Oliver") 
+
+    gesserit.logger.info("Playing audio...")
+    gesserit.play_audio(audio_file)

webscout/Provider/TTS/murfai.py

@@ -0,0 +1,139 @@
+import time
+import requests
+import pathlib
+from io import BytesIO
+from urllib.parse import urlencode
+from playsound import playsound
+from webscout import exceptions
+from webscout.AIbase import TTSProvider
+from webscout.Litlogger import LitLogger, LogFormat, ColorScheme
+from webscout.litagent import LitAgent
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from . import utils
+
+class MurfAITTS(TTSProvider):
+    """Text-to-speech provider using the MurfAITTS API."""
+    # Request headers
+    headers: dict[str, str] = {
+        "User-Agent": LitAgent().random()
+    }
+    cache_dir = pathlib.Path("./audio_cache")
+    all_voices: dict[str, str] = {"Hazel": "en-UK-hazel"}
+
+    def __init__(self, timeout: int = 20, proxies: dict = None):
+        """Initializes the MurfAITTS TTS client."""
+        self.session = requests.Session()
+        self.session.headers.update(self.headers)
+        if proxies:
+            self.session.proxies.update(proxies)
+        self.timeout = timeout
+        self.logger = LitLogger(
+            name="MurfAITTS",
+            format=LogFormat.MODERN_EMOJI,
+            color_scheme=ColorScheme.AURORA
+        )
+
+    def tts(self, text: str, voice: str = "Hazel", verbose:bool = True) -> str:
+        """Converts text to speech using the MurfAITTS API and saves it to a file."""
+        assert (
+            voice in self.all_voices
+        ), f"Voice '{voice}' not one of [{', '.join(self.all_voices.keys())}]"
+
+        filename = self.cache_dir / f"{int(time.time())}.mp3"
+
+        voice_id = self.all_voices[voice]
+
+        # Split text into sentences
+        sentences = utils.split_sentences(text)
+
+        # Function to request audio for each chunk
+        def generate_audio_for_chunk(part_text: str, part_number: int):
+            while True:
+                try:
+                    params: dict[str, str] = {
+                    "name": voice_id, 
+                    "text": part_text
+                    }
+                    encode_param: str = urlencode(params)
+                    response = self.session.get(f"https://murf.ai/Prod/anonymous-tts/audio?{encode_param}", headers=self.headers, timeout=self.timeout)
+                    response.raise_for_status()
+
+                    # Create the audio_cache directory if it doesn't exist
+                    self.cache_dir.mkdir(parents=True, exist_ok=True) 
+
+                    # Check if the request was successful
+                    if response.ok and response.status_code == 200:
+                        if verbose:
+                            self.logger.success(f"Chunk {part_number} processed successfully 🎉")
+                        return part_number, response.content
+                    else:
+                        if verbose:
+                            self.logger.warning(f"No data received for chunk {part_number}. Retrying...")
+                except requests.RequestException as e:
+                    if verbose:
+                        self.logger.error(f"Error for chunk {part_number}: {e}. Retrying... 🔄")
+                    time.sleep(1)
+        try:
+            # Using ThreadPoolExecutor to handle requests concurrently
+            with ThreadPoolExecutor() as executor:
+                futures = {executor.submit(generate_audio_for_chunk, sentence.strip(), chunk_num): chunk_num 
+                        for chunk_num, sentence in enumerate(sentences, start=1)}
+                
+                # Dictionary to store results with order preserved
+                audio_chunks = {}
+
+                for future in as_completed(futures):
+                    chunk_num = futures[future]
+                    try:
+                        part_number, audio_data = future.result()
+                        audio_chunks[part_number] = audio_data  # Store the audio data in correct sequence
+                    except Exception as e:
+                        if verbose:
+                            self.logger.error(f"Failed to generate audio for chunk {chunk_num}: {e} 🚨")
+
+            # Combine audio chunks in the correct sequence
+            combined_audio = BytesIO()
+            for part_number in sorted(audio_chunks.keys()):
+                combined_audio.write(audio_chunks[part_number])
+                if verbose:
+                    self.logger.debug(f"Added chunk {part_number} to the combined file.")
+
+            # Save the combined audio data to a single file
+            with open(filename, 'wb') as f:
+                f.write(combined_audio.getvalue())
+            if verbose:
+                self.logger.info(f"Final Audio Saved as {filename} 🔊")
+            return filename.as_posix()
+
+        except requests.exceptions.RequestException as e:
+            self.logger.critical(f"Failed to perform the operation: {e} 🚨")
+            raise exceptions.FailedToGenerateResponseError(
+                f"Failed to perform the operation: {e}"
+            )
+        
+    def play_audio(self, filename: str):
+        """
+        Plays an audio file using playsound.
+
+        Args:
+            filename (str): The path to the audio file.
+
+        Raises:
+            RuntimeError: If there is an error playing the audio.
+        """
+        try:
+            playsound(filename)
+        except Exception as e:
+            self.logger.error(f"Error playing audio: {e} 🔇")
+            raise RuntimeError(f"Error playing audio: {e}")
+
+# Example usage
+if __name__ == "__main__":
+    murfai = MurfAITTS()
+    text = "This is a test of the MurfAITTS text-to-speech API. It supports multiple sentences and advanced logging."
+
+    murfai.logger.info("Generating audio...")
+    audio_file = murfai.tts(text, voice="Hazel") 
+
+    murfai.logger.info("Playing audio...")
+    murfai.play_audio(audio_file)