Update app.py

app.py

@@ -1,156 +1,79 @@
 import gradio as gr
-import numpy as np
-import random
-
-
-from diffusers import DiffusionPipeline
-import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo" 
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = 666
-MAX_IMAGE_SIZE = 1280
-
-
-
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-examples = [
-    "two soldiers wearing gas masks, clad in military digital camo jungle fatigues, djing on futuristic mixers, synth, mpcs. location jungle rave.",
-    "in a dark jungle, a wizard and a warlock face each other as in a epic battle,  casting spells to operate vintage machines like mixers, synths, turntable.",
-    "A mesmerizing, bioluminescent DNA double helix, illuminated by a kaleidoscope of vibrant, pulsating light beams from colorful lasers, suspended in a futuristic, setting.",
-    "little rasta bunny dancing at a rave in the Jungle. cute street art, cartoon style.",
-]
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 600px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # ߙߛߕ-ߊ - ϕ - |θ_θ| - ϕ -  ")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1.3,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1.3,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1.6,
-                value=0.3,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=600,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=1.3,
-                    value=600,  
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=400,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=1.6,
-                    value=400, 
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=2,
-                    step=0.6,
-                    value=0.3, 
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=6,
-                    step=3,
-                    value=3,  
-                )
+import edge_tts
+import asyncio
+import tempfile
+import os
+
+# Get all available voices
+async def get_voices():
+    voices = await edge_tts.list_voices()
+    return {f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] for v in voices}
+
+# Text-to-speech function
+async def text_to_speech(text, voice, rate, pitch):
+    if not text.strip():
+        return None, gr.Warning("Please enter text to convert.")
+    if not voice:
+        return None, gr.Warning("Please select a voice.")
+    
+    voice_short_name = voice.split(" - ")[0]
+    rate_str = f"{rate:+d}%"
+    pitch_str = f"{pitch:+d}Hz"
+    communicate = edge_tts.Communicate(text, voice_short_name, 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
+
+# Gradio interface function
+def tts_interface(text, voice, rate, pitch):
+    audio, warning = asyncio.run(text_to_speech(text, voice, rate, pitch))
+    return audio, warning
+
+# Create Gradio application
+import gradio as gr
 
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
+async def create_demo():
+    voices = await get_voices()
+    
+    description = X talkBox
+    Convert text to speech using Microsoft Edge TTS. Adjust speech rate and pitch: 0 is default, positive values increase, negative values decrease.
+    
+    🎥 **Exciting News: Introducing our Text-to-Video Converter!** 🎥
+    
+    Take your content creation to the next level with our cutting-edge Text-to-Video Converter! 
+    Transform your words into stunning, professional-quality videos in just a few clicks. 
+    
+    ✨ Features:
+    • Convert text to engaging videos with customizable visuals
+    • Choose from 40+ languages and 300+ voices
+    • Perfect for creating audiobooks, storytelling, and language learning materials
+    • Ideal for educators, content creators, and language enthusiasts
+    
+    Ready to revolutionize your content? [Click here to try our Text-to-Video Converter now!](https://text2video.wingetgui.com/)
+    """
+    
+    demo = gr.Interface(
+        fn=tts_interface,
         inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
+            gr.Textbox(label="Input Text", lines=5),
+            gr.Dropdown(choices=[""] + list(voices.keys()), label="Select Voice", value=""),
+            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.Audio(label="Generated Audio", type="filepath"),
+            gr.Markdown(label="Warning", visible=False)
         ],
-        outputs=[result, seed],
+        title="Edge TTS Text-to-Speech",
+        description=description,
+        article="Experience the power of Edge TTS for text-to-speech conversion, and explore our advanced Text-to-Video Converter for even more creative possibilities!",
+        analytics_enabled=False,
+        allow_flagging="manual"
     )
+    return demo
 
+# Run the application
 if __name__ == "__main__":
-    demo.launch()
-    
+    demo = asyncio.run(create_demo())
+    demo.launch()