Add application file

README.md

@@ -1,14 +1,94 @@
----
-title: ContentVoiceGen
-emoji: 🐠
-colorFrom: gray
-colorTo: indigo
-sdk: gradio
-sdk_version: 5.17.1
-app_file: app.py
-pinned: false
-license: apache-2.0
-short_description: AIpowered text-to-speech generator for storytelling, podcast
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🎙️ AI VoiceCraft: Text-to-Speech Studio 🚀
+
+## Overview
+
+AI VoiceCraft is a powerful web application built with Gradio that leverages cutting-edge AI to generate dynamic text content and transform it into natural-sounding speech. This tool integrates the Gemini AI model for content generation and Microsoft Edge TTS for high-quality audio synthesis.
+
+## Features
+
+-   **Dynamic Content Generation:**
+    -      Generate various content types, including stories, news, podcasts, and more.
+    -      Customize content length, theme, and style.
+    -      Utilize Gemini AI for creative and contextually relevant text output.
+-   **High-Quality Text-to-Speech:**
+    -      Leverage Microsoft Edge TTS for realistic voice synthesis.
+    -      Support for multiple languages and voices.
+    -      Fine-tune speech rate and pitch for optimal delivery.
+-   **User-Friendly Interface:**
+    -      Intuitive Gradio interface for easy navigation and control.
+    -      Real-time feedback and error handling.
+    -   Attractive theme applied for better user experience.
+-   **Customization Options:**
+    -      Adjust the creativity level of the AI content generation.
+    -   Input custom prompts for fine tuning the AI outputs.
+    -   Adjust speech rate and pitch to fit your needs.
+
+## Getting Started
+
+### Prerequisites
+
+-      Python 3.7+
+-      Internet connection (for API access and TTS)
+-   API Key for Gemini Model.
+
+### Installation
+
+1.  Clone the repository:
+
+    ```bash
+    git clone <repository_url>
+    cd <repository_directory>
+    ```
+
+2.  Install the required Python packages:
+
+    ```bash
+    pip install gradio requests edge-tts google-generativeai nest_asyncio
+    ```
+3. set your API key in the VOCALIS.py file.
+4. Run the application:
+
+    ```bash
+    python app.py
+    ```
+
+
+5. Open your web browser and navigate to the local URL provided by Gradio (usually `http://127.0.0.1:7860`).
+
+## Usage
+
+1.  Select the desired content type from the dropdown menu.
+2.  Choose the language and voice for the TTS output.
+3.  Adjust the output style, content length, and theme as needed.
+4.  Enter any custom text or instructions in the customization field.
+5.  Adjust the speech rate and pitch using the sliders.
+6.  Click the "Submit" button to generate the text and audio.
+7.  Review the generated text and listen to the audio output.
+
+## Code Structure
+
+-   `your_script_name.py`: Main application script that integrates Gradio, content generation, and TTS.
+-   `VOCALIS.py`: Contains the `Agent` and `ContentGenerator` classes for AI content generation.
+-   `edgeTTsLang.py`: Dictionary containing the language and voice codes for Microsoft Edge TTS.
+
+## Dependencies
+
+-   `gradio`: For building the web interface.
+-   `requests`: For making HTTP requests to the API.
+-   `edge-tts`: For text-to-speech conversion.
+-   `google-generativeai`: For interacting with the Gemini AI model.
+-   `asyncio`: For asynchronous operations.
+-   `nest_asyncio`: For handling nested asyncio events in Jupyter notebooks.
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit pull requests or open issues for bug fixes, feature requests, or improvements.
+
+## License
+
+This project is licensed under the MIT License.
+
+## Gradio Theme
+
+To enhance the user experience, an attractive theme has been applied to the Gradio interface. You can customize the theme further by modifying the Gradio theme settings in the `create_demo` function.
+

VOCALIS/__init__.py

@@ -0,0 +1,2 @@
+from .agent import Agent
+from .task import ContentGenerator

VOCALIS/agent.py

@@ -0,0 +1,5 @@
+class Agent:
+    def __init__(self, model: str, temperature: float = 0.6, role: str = "Content Creator"):
+        self.model = model
+        self.temperature = temperature
+        self.role = role

VOCALIS/task.py

@@ -0,0 +1,121 @@
+from VOCALIS import Agent
+import os
+import logging
+import re
+import google.generativeai as genai
+from google.generativeai.types import GenerationConfig
+
+
+# Configure Gemini AI API
+api_key = os.getenv("API_KEY")
+if not api_key:
+    raise ValueError("API Key is missing. Set the API_KEY environment variable.")
+genai.configure(api_key=api_key)
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
+
+
+class ContentGenerator:
+    def __init__(self, agent: Agent, content_type: str = "story", language: str = "English",content_length: int = 200,
+                 theme: str = "General/None", expectations: str = ""):
+        self.agent = agent
+        self.content_type = content_type.strip().lower()
+        self.language = language.strip()
+        self.goal = self._get_default_goal()
+        self.content_length = content_length  # Added content length
+        self.theme = theme.strip()
+        self.expectations = expectations.strip()
+
+        # Input validation
+        if self.content_type not in [
+            "story", "social", "news", "motivational", "explainer", "advertisement", "interview", "podcast",
+            "testimonial", "comedy", "audiobook", "documentary", "meditation", "education", "poem", "recipe", "script",
+            "summary", "email", "blog"
+        ]:
+            raise ValueError(f"Invalid content type: {self.content_type}")
+        # if self.language not in languages:
+        #     raise ValueError(f"Invalid language: {self.language}")
+
+    def _get_default_goal(self) -> str:
+        default_goals = {
+            "story": "Generate a vivid, engaging, and natural-sounding short story suitable for narration.",
+            "social": "Create a casual, engaging, and conversational social media script that sounds authentic.",
+            "news": "Write a professional and well-structured news report optimized for audio presentation.",
+            "motivational": "Generate an inspiring and natural motivational speech with a strong emotional connection.",
+            "explainer": "Break down a complex topic in a clear and engaging way, suitable for an audio explanation.",
+            "advertisement": "Write a persuasive and compelling ad script that feels engaging and natural.",
+            "interview": "Generate a structured, conversational interview with natural question-answer flow.",
+            "podcast": "Write a structured podcast script with natural dialogue and engaging discussions.",
+            "testimonial": "Create an authentic-sounding customer testimonial suitable for an audio review.",
+            "comedy": "Write a humorous monologue or short sketch with a natural comedic timing.",
+            "audiobook": "Generate a structured audiobook chapter with expressive dialogue and immersive narration.",
+            "documentary": "Create a professional and informative documentary narration with a storytelling approach.",
+            "meditation": "Write a soothing guided meditation script designed for relaxation and mindfulness.",
+            "education": "Generate a structured and clear educational script that is easy to follow in an audio format.",
+            "poem": "Generate a beautiful and expressive poem with a natural flow.",
+            "recipe": "Write a clear and easy-to-follow recipe suitable for audio instructions.",
+            "script": "Generate a well-structured script for a short video or audio segment.",
+            "summary": "Create a concise and accurate summary of a given topic.",
+            "email": "Write a professional and well-formatted email.",
+            "blog": "Generate an engaging and informative blog post."
+        }
+        return default_goals.get(self.content_type,
+                                 "Generate a vivid, engaging, and natural-sounding short story suitable for narration.")
+
+    def _build_prompt(self) -> str:
+        prompt = (
+            f"Role: You are a professional voice-over script writer specializing in {self.content_type} generation for natural speech synthesis.\n"
+            f"Task: Create a high-quality, natural-sounding script in {self.language} optimized for text-to-speech (TTS).\n"
+            f"Tone: Maintain a conversational and engaging tone, as if speaking directly to a listener.\n"
+            f"Structure: Use short, clear sentences. Organize the content into logical paragraphs for easy audio comprehension.\n"
+            f"Goal: {self.goal}\n"
+            f"Constraints:\n"
+            f"- Keep the script under {self.content_length} words.\n"
+            f"- Use simple, direct language. Avoid complex jargon or unusual words that may be mispronounced by TTS.\n"
+            f"- Do not explicitly state the content type (e.g., 'This is a story', 'Here is a script for voice-over...', etc.).\n"
+            f"- Avoid excessive use of abbreviations, as they may not be pronounced correctly by TTS.\n"
+            f"- Ensure smooth sentence transitions to maintain a natural flow when spoken aloud.\n"
+
+            f"Instructions for Natural Pacing and Pauses:\n"
+            f"- Use punctuation strategically (commas, ellipses, and dashes) to guide pauses in speech.\n"
+            f"- Insert line breaks between key ideas to improve speech rhythm and avoid monotony.\n"
+            f"- Break down long sentences into shorter, more digestible phrases to improve clarity.\n"
+
+            f"Instructions for Emphasis:\n"
+            f"- Use ALL CAPS or spacing between letters for words that should be emphasized.\n"
+            f"- Provide phonetic hints for difficult or unusual words if necessary.\n"
+
+            f"Output:\n"
+            f"- Return ONLY the generated script. Do not include any introductory phrases like 'Here is a script...' or explanations.\n"
+        )
+
+        if self.theme and self.theme != "General/None":
+            prompt += f"Theme/Nature: {self.theme}\n"
+
+        if self.expectations:
+            prompt += f"User Expectations: {self.expectations}\n"
+
+        return prompt
+
+
+
+    def generate_content(self) -> str:
+        try:
+            model = genai.GenerativeModel(self.agent.model)
+            prompt = self._build_prompt()
+            contents = [{"parts": [{"text": prompt}]}]
+            generation_config = GenerationConfig(temperature=self.agent.temperature, max_output_tokens=1024)
+
+            response = model.generate_content(contents=contents, generation_config=generation_config)
+            output = response.text
+
+            output = output.strip()
+            output = re.sub(r'\s+', ' ', output)
+
+            return output
+
+        except Exception as e:
+            logging.error(f"Error generating content: {e}")
+            return f"Generation failed: {e}"
+
+

app.py

@@ -0,0 +1,155 @@
+import gradio as gr
+import asyncio
+import tempfile
+import logging
+import requests
+from VOCALIS import Agent, ContentGenerator
+from edgeTTsLang import languages
+
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
+logger = logging.getLogger(__name__)
+
+def generate_the_content(content_type, language,output_style,content_length, theme, expectations):
+    try:
+        temperature_map = {
+            "Precise (Deterministic)": 0.1,
+            "Very Focused (Low Randomness)": 0.3,
+            "Moderately Focused (Slight Randomness)": 0.4,
+            "Balanced (Moderate Creativity)": 0.5,
+            "Slightly Creative (Moderate Randomness)": 0.6,
+            "Creative (High Randomness)": 0.7,
+            "Highly Creative (Very High Randomness)": 0.8,
+            "Experimental (Maximum Randomness)": 0.95,
+        }
+        temperature = temperature_map.get(output_style, 0.6)
+        agent = Agent(model="gemini-2.0-flash", temperature=temperature)
+        generator = ContentGenerator(agent, content_type, language, content_length, theme, expectations)
+        output = generator.generate_content()
+
+        return output
+
+    except ValueError as ve:
+        return f"Input Error: {ve}"
+    except requests.exceptions.ConnectionError:
+        return "Network Error: Could not connect to API. Please check your internet connection."
+    except Exception as e:
+        return f"General Error: {e}"
+
+async def text_to_speech(text, voice, rate, pitch):
+    import edge_tts
+    if not text.strip():
+        return None, "Please enter text to convert."
+    if not voice:
+        return None, "Please select a voice."
+    rate_str = f"{rate:+d}%"
+    pitch_str = f"{pitch:+d}Hz"
+    communicate = edge_tts.Communicate(text, voice, rate=rate_str, pitch=pitch_str)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
+        tmp_path = tmp_file.name
+        await communicate.save(tmp_path)
+    return tmp_path, None
+
+async def tts_interface(content_type, language, voice, output_style, content_length, theme, Customization, rate, pitch):
+    text_output = generate_the_content(content_type, language, output_style, content_length, theme, Customization)
+    if text_output.startswith("Error:"):
+        return None, None, gr.Markdown(text_output)
+
+    audio_file, warning = await text_to_speech(text_output, languages[language][voice], rate, pitch)
+
+    if warning:
+        return text_output, gr.Markdown(warning)
+
+    return text_output, audio_file, None
+
+def create_demo():
+    language_choices = list(languages.keys())
+
+    custom_theme = gr.themes.Soft(
+        primary_hue="indigo",
+        secondary_hue="blue",
+        neutral_hue="slate",
+        radius_size=gr.themes.sizes.radius_sm,
+        font=[gr.themes.GoogleFont("Montserrat"), "Arial", "sans-serif"],
+    )
+
+    demo = gr.Interface(
+        fn=tts_interface,
+        theme=custom_theme,
+        inputs=[
+            gr.Dropdown(label="Content Type", choices=[
+                "story", "social", "news", "motivational", "explainer", "advertisement", "interview", "podcast",
+                "testimonial", "comedy", "audiobook", "documentary", "meditation", "education", "poem", "recipe",
+                "script", "summary", "email", "blog"
+            ], value="story"),
+            gr.Dropdown(label="Language", choices=language_choices, value=language_choices[0] if language_choices else ""),
+            gr.Dropdown(label="Voice", choices=["Female", "Male"], value="Female"),
+            gr.Dropdown(label="Output Style", choices=[
+                "Precise (Deterministic)", "Very Focused (Low Randomness)", "Moderately Focused (Slight Randomness)",
+                "Balanced (Moderate Creativity)", "Slightly Creative (Moderate Randomness)",
+                "Creative (High Randomness)", "Highly Creative (Very High Randomness)",
+                "Experimental (Maximum Randomness)"
+            ], value="Balanced (Moderate Creativity)"),
+            gr.Slider(label="Content Length (Words)", minimum=100, maximum=1000, value=200, step=10),
+            gr.Dropdown(label="Theme/Nature (Optional)", choices=[
+                "General/None", "Narrative/Storytelling", "Informative/Educational", "Descriptive/Atmospheric",
+                "Persuasive/Argumentative", "Humorous/Comedic", "Emotional/Inspirational", "Technical/Scientific",
+                "Historical/Cultural", "Modern/Contemporary", "Futuristic/Sci-Fi", "Fantasy/Mythical",
+                "Mystery/Suspense", "Adventure/Exploration", "Realistic/Documentary", "Philosophical/Reflective",
+                "Social/Relational", "Environmental/Nature", "Personal/Anecdotal"
+            ], value="General/None"),
+            gr.Textbox(label="Customization", placeholder="Add any extra information to help customize the generated content"),
+            gr.Slider(minimum=-50, maximum=50, value=0, label="Speech Rate Adjustment (%)", step=1),
+            gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1)
+        ],
+        outputs=[
+            gr.Textbox(label="Generated Text"),
+            gr.Audio(label="Generated Audio", type="filepath"),
+            gr.Markdown(label="Error/Warning", visible=True)
+        ],
+        title="✨ AI VoiceCraft: Text-to-Speech Studio 🎙️",
+        description="""  
+        🚀 Transform your text into captivating audio! 🚀  
+
+        This tool generates AI-powered content and converts it into lifelike speech using Microsoft Edge TTS.  
+
+        🔹 **Features at a Glance:**  
+        🌍 Supports multiple languages and voices  
+        🎚️ Adjust speech rate and pitch for natural delivery  
+        📝 Generate dynamic content: stories, news, podcasts & more  
+        🎭 Customize tone, length, and style to fit your needs  
+
+        """,
+        article="""  
+        # 🌟 Welcome to AI VoiceCraft! 🌟  
+
+        **Unleash the power of AI-driven text-to-speech.**  
+
+        This advanced application blends **cutting-edge AI content generation** with high-quality speech synthesis to create immersive audio experiences.  
+
+        ## 🎤 Key Highlights:  
+        🔊 Natural and expressive voice output  
+        📖 AI-powered script generation tailored for speech  
+        ⚙️ Fine-tune pitch, rate, and delivery style  
+
+        🔗 [Discover more AI tools@MusabbirKM](https://www.example.com/ai-tools)  
+        """,
+
+        allow_flagging="never",
+        api_name=None,
+    )
+    return demo
+
+async def main():
+    demo = create_demo()
+    demo.queue(default_concurrency_limit=5)
+    demo.launch(show_api=False)
+
+
+if __name__ == "__main__":
+    try:
+        asyncio.run(main())
+    except RuntimeError:
+        import nest_asyncio
+        nest_asyncio.apply()
+        asyncio.run(main())

edgeTTsLang.py

@@ -0,0 +1,272 @@
+languages = {
+    "Malayalam (India)": {
+            "Female": "ml-IN-SobhanaNeural",
+            "Male": "ml-IN-MidhunNeural"
+        },
+    "Hindi (India)": {
+            "Female": "hi-IN-SwaraNeural",
+            "Male": "hi-IN-MadhurNeural"
+        },
+    "Kannada (India)": {
+            "Female": "kn-IN-SapnaNeural",
+            "Male": "kn-IN-GaganNeural"
+        },
+    "Tamil (India)": {
+            "Female": "ta-IN-PallaviNeural",
+            "Male": "ta-IN-ValluvarNeural"
+        },
+    "Telugu (India)": {
+            "Female": "te-IN-ShrutiNeural",
+            "Male": "te-IN-MohanNeural"
+        },
+    "Urdu (India)": {
+            "Female": "ur-IN-GulNeural",
+            "Male": "ur-IN-SarfarazNeural"
+        },
+    "Gujarati (India)": {
+            "Female": "gu-IN-DhwaniNeural",
+            "Male": "gu-IN-NiranjanNeural"
+        },
+    "Marathi (India)": {
+            "Female": "mr-IN-AarohiNeural",
+            "Male": "mr-IN-ManoharNeural"
+        },
+    "Odia (India)": {
+            "Female": "or-IN-TariniNeural",
+            "Male": "or-IN-BiswajitNeural"
+        },
+    "Punjabi (India)": {
+            "Female": "pa-IN-GagandeepNeural",
+            "Male": "pa-IN-NirvairNeural"
+        },
+    "Assamese (India)": {
+            "Female": "as-IN-PariNeural",
+            "Male": "as-IN-NiloyNeural"
+        },
+    "Afrikaans (South Africa)": {
+        "Female": "af-ZA-AdriNeural",
+        "Male": "af-ZA-WillemNeural"
+    },
+    "Albanian (Albania)": {
+        "Female": "sq-AL-AnilaNeural",
+        "Male": "sq-AL-IlirNeural"
+    },
+    "Amharic (Ethiopia)": {
+        "Female": "am-ET-MekdesNeural",
+        "Male": "am-ET-AmehaNeural"
+    },
+    "Arabic (Algeria)": {
+        "Female": "ar-DZ-AminaNeural",
+        "Male": "ar-DZ-IsmaelNeural"
+    },
+    "Arabic (Bahrain)": {
+        "Female": "ar-BH-LailaNeural",
+        "Male": "ar-BH-AliNeural"
+    },
+    "Arabic (Egypt)": {
+        "Female": "ar-EG-SalmaNeural",
+        "Male": "ar-EG-ShakirNeural"
+    },
+    "Arabic (Iraq)": {
+        "Female": "ar-IQ-RanaNeural",
+        "Male": "ar-IQ-BasselNeural"
+    },
+    "Arabic (Jordan)": {
+        "Female": "ar-JO-SanaNeural",
+        "Male": "ar-JO-TaimNeural"
+    },
+    "Arabic (Kuwait)": {
+        "Female": "ar-KW-NouraNeural",
+        "Male": "ar-KW-FahedNeural"
+    },
+    "Arabic (Lebanon)": {
+        "Female": "ar-LB-LaylaNeural",
+        "Male": "ar-LB-RamiNeural"
+    },
+    "Arabic (Libya)": {
+        "Female": "ar-LY-ImanNeural",
+        "Male": "ar-LY-OmarNeural"
+    },
+    "Arabic (Morocco)": {
+        "Female": "ar-MA-MounaNeural",
+        "Male": "ar-MA-JamalNeural"
+    },
+    "Arabic (Oman)": {
+        "Female": "ar-OM-AyshaNeural",
+        "Male": "ar-OM-SultanNeural"
+    },
+    "Arabic (Qatar)": {
+        "Female": "ar-QA-AmalNeural",
+        "Male": "ar-QA-MoazNeural"
+    },
+    "Arabic (Saudi Arabia)": {
+        "Female": "ar-SA-HodaNeural",
+        "Male": "ar-SA-FahdNeural"
+    },
+    "Arabic (Syria)": {
+        "Female": "ar-SY-AmanyNeural",
+        "Male": "ar-SY-LaithNeural"
+    },
+    "Arabic (Tunisia)": {
+        "Female": "ar-TN-ReemNeural",
+        "Male": "ar-TN-HediNeural"
+    },
+    "Arabic (UAE)": {
+        "Female": "ar-AE-FatimaNeural",
+        "Male": "ar-AE-HamdanNeural"
+    },
+    "Arabic (Yemen)": {
+        "Female": "ar-YE-MaryamNeural",
+        "Male": "ar-YE-SalehNeural"
+    },
+    "Armenian (Armenia)": {
+        "Female": "hy-AM-AnahitNeural",
+        "Male": "hy-AM-HaykNeural"
+    },
+    "Basque (Spain)": {
+        "Female": "eu-ES-AinhoaNeural",
+        "Male": "eu-ES-AnderNeural"
+    },
+    "Bengali (Bangladesh)": {
+        "Female": "bn-BD-NabanitaNeural",
+        "Male": "bn-BD-PradeepNeural"
+    },
+    "Bengali (India)": {
+        "Female": "bn-IN-BashantiNeural",
+        "Male": "bn-IN-TanishNeural"
+    },
+    "English (India)": {
+        "Female": "en-IN-NeerjaNeural",
+        "Male": "en-IN-PrabhatNeural"
+    },
+    "English (Australia)": {
+        "Female": "en-AU-NatashaNeural",
+        "Male": "en-AU-WilliamNeural"
+    },
+    "English (Canada)": {
+        "Female": "en-CA-ClaraNeural",
+        "Male": "en-CA-LiamNeural"
+    },
+    "English (Ireland)": {
+        "Female": "en-IE-EmilyNeural",
+        "Male": "en-IE-ConnorNeural"
+    },
+    "English (New Zealand)": {
+        "Female": "en-NZ-MollyNeural",
+        "Male": "en-NZ-MitchellNeural"
+    },
+    "English (South Africa)": {
+        "Female": "en-ZA-LeahNeural",
+        "Male": "en-ZA-LukeNeural"
+    },
+    "English (United Kingdom)": {
+        "Female": "en-GB-LibbyNeural",
+        "Male": "en-GB-RyanNeural"
+    },
+    "English (United States)": {
+        "Female": "en-US-JennyNeural",
+        "Male": "en-US-GuyNeural"
+    },
+    "English (Uganda)": {
+            "Female": "en-UG-EmilyNeural",
+            "Male": "en-UG-ConnorNeural"
+        },
+    "Bosnian (Bosnia and Herzegovina)": {
+        "Female": "bs-BA-VesnaNeural",
+        "Male": "bs-BA-GoranNeural"
+    },
+    "Bulgarian (Bulgaria)": {
+        "Female": "bg-BG-KalinaNeural",
+        "Male": "bg-BG-BorislavNeural"
+    },
+    "Catalan (Spain)": {
+        "Female": "ca-ES-AlbaNeural",
+        "Male": "ca-ES-EnricNeural"
+    },
+    "Chinese (Cantonese, Traditional)": {
+        "Female": "yue-HK-HiuGaaiNeural",
+        "Male": "yue-HK-WanLungNeural"
+    },
+    "Chinese (Mandarin, Simplified)": {
+        "Female": "zh-CN-XiaoxiaoNeural",
+        "Male": "zh-CN-YunxiNeural"
+    },
+    "Chinese (Mandarin, Traditional)": {
+        "Female": "zh-TW-HsiaoYuNeural",
+        "Male": "zh-TW-YunJheNeural"
+    },
+    "Croatian (Croatia)": {
+        "Female": "hr-HR-GabrijelaNeural",
+        "Male": "hr-HR-SreckoNeural"
+    },
+    "Czech (Czech Republic)": {
+        "Female": "cs-CZ-VlastaNeural",
+        "Male": "cs-CZ-AntoninNeural"
+    },
+    "Danish (Denmark)": {
+        "Female": "da-DK-ChristelNeural",
+        "Male": "da-DK-JeppeNeural"
+    },
+    "Dutch (Belgium)": {
+        "Female": "nl-BE-DenaNeural",
+        "Male": "nl-BE-ArnaudNeural"
+    },
+    "Dutch (Netherlands)": {
+        "Female": "nl-NL-ColetteNeural",
+        "Male": "nl-NL-MaartenNeural"
+    },
+    "Estonian (Estonia)": {
+        "Female": "et-EE-AnuNeural",
+        "Male": "et-EE-KertNeural"
+    },
+    "Filipino (Philippines)": {
+        "Female": "fil-PH-BlessicaNeural",
+        "Male": "fil-PH-AngeloNeural"
+    },
+    "Finnish (Finland)": {
+        "Female": "fi-FI-NooraNeural",
+        "Male": "fi-FI-HarriNeural"
+    },
+    "French (Belgium)": {
+        "Female": "fr-BE-CharlineNeural",
+        "Male": "fr-BE-GerardNeural"
+    },
+    "French (Canada)": {
+        "Female": "fr-CA-SylvieNeural",
+        "Male": "fr-CA-AntoineNeural"
+    },
+    "French (France)": {
+        "Female": "fr-FR-DeniseNeural",
+        "Male": "fr-FR-HenriNeural"
+    },
+    "Galician (Spain)": {
+        "Female": "gl-ES-RoiNeural",
+        "Male": "gl-ES-SabelaNeural"
+    },
+    "Georgian (Georgia)": {
+        "Female": "ka-GE-EkaNeural",
+        "Male": "ka-GE-GiorgiNeural"
+    },
+    "German (Austria)": {
+        "Female": "de-AT-IngridNeural",
+        "Male": "de-AT-JonasNeural"
+    },
+    "German (Germany)": {
+        "Female": "de-DE-KatjaNeural",
+        "Male": "de-DE-ConradNeural"
+    },
+    "German (Switzerland)": {
+        "Female": "de-CH-LeniNeural",
+        "Male": "de-CH-JanNeural"
+    },
+    "Indonesian (Indonesia)": {
+            "Female": "id-ID-GadisNeural",
+            "Male": "id-ID-ArdiNeural"
+        },
+    "Japanese (Japan)": {
+            "Female": "ja-JP-NanamiNeural",
+            "Male": "ja-JP-KeitaNeural"
+        },
+}
+
+

requirements.txt

@@ -0,0 +1,5 @@
+gradio~=5.16.0
+requests~=2.32.3
+yt-dlp~=2025.1.26
+
+