Update app.py

app.py

@@ -1,333 +1,830 @@
+import os
 import gradio as gr
-import numpy as np
-import random
-import torch
 import spaces
+from infer_rvc_python import BaseLoader
+import random
+import logging
+import time
+import soundfile as sf
+from infer_rvc_python.main import download_manager, load_hu_bert, Config
+import zipfile
+import edge_tts
+import asyncio
+import librosa
+import traceback
+import soundfile as sf
+from pedalboard import Pedalboard, Reverb, Compressor, HighpassFilter
+from pedalboard.io import AudioFile
+from pydub import AudioSegment
+import noisereduce as nr
+import numpy as np
+import urllib.request
+import shutil
+import threading
+import argparse
+import sys
+
+parser = argparse.ArgumentParser(description="Run the app with optional sharing")
+parser.add_argument(
+    '--share',
+    action='store_true',
+    help='Enable sharing mode'
+)
+parser.add_argument(
+    '--theme',
+    type=str,
+    default="aliabid94/new-theme",
+    help='Set the theme (default: aliabid94/new-theme)'
+)
+args = parser.parse_args()
+
+IS_COLAB = True if ('google.colab' in sys.modules or args.share) else False
+IS_ZERO_GPU = os.getenv("SPACES_ZERO_GPU")
+
+logging.getLogger("infer_rvc_python").setLevel(logging.ERROR)
+
+converter = BaseLoader(only_cpu=False, hubert_path=None, rmvpe_path=None)
+converter.hu_bert_model = load_hu_bert(Config(only_cpu=False), converter.hubert_path)
+
+# مدل پیش‌فرض (اختیاری)
+test_model = "https://huggingface.co/sail-rvc/Aldeano_Minecraft__RVC_V2_-_500_Epochs_/resolve/main/model.pth?download=true,   https://huggingface.co/sail-rvc/Aldeano_Minecraft__RVC_V2_-_500_Epochs_/resolve/main/model.index?download=true"
+test_names = ["model.pth", "model.index"]
+
+for url, filename in zip(test_model.split(", "), test_names):
+    try:
+        download_manager(
+            url=url,
+            path=".",
+            extension="",
+            overwrite=False,
+            progress=True,
+        )
+        if not os.path.isfile(filename):
+            raise FileNotFoundError
+    except Exception:
+        with open(filename, "wb") as f:
+            pass
+
+title = "<center><strong><font size='7'>RVC⚡ZERO - High Quality Voice Conversion</font></strong></center>"
+description = "Upload your own model (.pth) and audio files for voice conversion." if IS_ZERO_GPU else ""
+RESOURCES = """
+📌 <strong>Tips for Best Quality:</strong>
+- Use models trained for 200+ epochs.
+- Always upload .index file & set Index Influence to 0.9.
+- Choose "rmvpe+" as Pitch Algorithm.
+- Output format: WAV (lossless).
+- Disable noise reduction unless necessary.
+- Keep Resample SR = 0 (automatic).
+"""
+theme = args.theme
+delete_cache_time = (3200, 3200) if IS_ZERO_GPU else (86400, 86400)
+
+PITCH_ALGO_OPT = [
+    "pm",
+    "harvest",
+    "crepe",
+    "rmvpe",
+    "rmvpe+",
+]
+
+
+async def get_voices_list(proxy=None):
+    """Print all available voices."""
+    from edge_tts import list_voices
+    voices = await list_voices(proxy=proxy)
+    voices = sorted(voices, key=lambda voice: voice.get("ShortName", ""))
+
+    table = [
+        {
+            "ShortName": voice.get("ShortName", "Unknown"),
+            "Gender": voice.get("Gender", "Unknown"),
+            "ContentCategories": ", ".join(voice.get("VoiceTag", {}).get("ContentCategories", [])),
+            "VoicePersonalities": ", ".join(voice.get("VoiceTag", {}).get("VoicePersonalities", [])),
+            "FriendlyName": voice.get("FriendlyName", voice.get("Name", "Unknown Voice")),
+        }
+        for voice in voices
+    ]
+
+    return table
+
+
+def find_files(directory):
+    file_paths = []
+    for filename in os.listdir(directory):
+        if filename.endswith('.pth') or filename.endswith('.zip') or filename.endswith('.index'):
+            file_paths.append(os.path.join(directory, filename))
+    return file_paths
+
+
+def unzip_in_folder(my_zip, my_dir):
+    with zipfile.ZipFile(my_zip) as zip:
+        for zip_info in zip.infolist():
+            if zip_info.is_dir():
+                continue
+            zip_info.filename = os.path.basename(zip_info.filename)
+            zip.extract(zip_info, my_dir)
 
-from PIL import Image
-from diffusers import QwenImageEditPlusPipeline
 
-import os
-import base64
-import json
-
-SYSTEM_PROMPT = '''
-# Edit Instruction Rewriter
-You are a professional edit instruction rewriter. Your task is to generate a precise, concise, and visually achievable professional-level edit instruction based on the user-provided instruction and the image to be edited.  
-
-Please strictly follow the rewriting rules below:
-
-## 1. General Principles
-- Keep the rewritten prompt **concise and comprehensive**. Avoid overly long sentences and unnecessary descriptive language.  
-- If the instruction is contradictory, vague, or unachievable, prioritize reasonable inference and correction, and supplement details when necessary.  
-- Keep the main part of the original instruction unchanged, only enhancing its clarity, rationality, and visual feasibility.  
-- All added objects or modifications must align with the logic and style of the scene in the input images.  
-- If multiple sub-images are to be generated, describe the content of each sub-image individually.  
-
-## 2. Task-Type Handling Rules
-
-### 1. Add, Delete, Replace Tasks
-- If the instruction is clear (already includes task type, target entity, position, quantity, attributes), preserve the original intent and only refine the grammar.  
-- If the description is vague, supplement with minimal but sufficient details (category, color, size, orientation, position, etc.). For example:  
-    > Original: "Add an animal"  
-    > Rewritten: "Add a light-gray cat in the bottom-right corner, sitting and facing the camera"  
-- Remove meaningless instructions: e.g., "Add 0 objects" should be ignored or flagged as invalid.  
-- For replacement tasks, specify "Replace Y with X" and briefly describe the key visual features of X.  
-
-### 2. Text Editing Tasks
-- All text content must be enclosed in English double quotes `" "`. Keep the original language of the text, and keep the capitalization.  
-- Both adding new text and replacing existing text are text replacement tasks, For example:  
-    - Replace "xx" to "yy"  
-    - Replace the mask / bounding box to "yy"  
-    - Replace the visual object to "yy"  
-- Specify text position, color, and layout only if user has required.  
-- If font is specified, keep the original language of the font.  
-
-### 3. Human Editing Tasks
-- Make the smallest changes to the given user's prompt.  
-- If changes to background, action, expression, camera shot, or ambient lighting are required, please list each modification individually.
-- **Edits to makeup or facial features / expression must be subtle, not exaggerated, and must preserve the subject’s identity consistency.**
-    > Original: "Add eyebrows to the face"  
-    > Rewritten: "Slightly thicken the person’s eyebrows with little change, look natural."
-
-### 4. Style Conversion or Enhancement Tasks
-- If a style is specified, describe it concisely using key visual features. For example:  
-    > Original: "Disco style"  
-    > Rewritten: "1970s disco style: flashing lights, disco ball, mirrored walls, vibrant colors"  
-- For style reference, analyze the original image and extract key characteristics (color, composition, texture, lighting, artistic style, etc.), integrating them into the instruction.  
-- **Colorization tasks (including old photo restoration) must use the fixed template:**  
-  "Restore and colorize the old photo."  
-- Clearly specify the object to be modified. For example:  
-    > Original: Modify the subject in Picture 1 to match the style of Picture 2.  
-    > Rewritten: Change the girl in Picture 1 to the ink-wash style of Picture 2 — rendered in black-and-white watercolor with soft color transitions.
-
-### 5. Material Replacement
-- Clearly specify the object and the material. For example: "Change the material of the apple to papercut style."
-- For text material replacement, use the fixed template:
-    "Change the material of text "xxxx" to laser style"
-
-### 6. Logo/Pattern Editing
-- Material replacement should preserve the original shape and structure as much as possible. For example:
-   > Original: "Convert to sapphire material"  
-   > Rewritten: "Convert the main subject in the image to sapphire material, preserving similar shape and structure"
-- When migrating logos/patterns to new scenes, ensure shape and structure consistency. For example:
-   > Original: "Migrate the logo in the image to a new scene"  
-   > Rewritten: "Migrate the logo in the image to a new scene, preserving similar shape and structure"
-
-### 7. Multi-Image Tasks
-- Rewritten prompts must clearly point out which image’s element is being modified. For example:  
-    > Original: "Replace the subject of picture 1 with the subject of picture 2"  
-    > Rewritten: "Replace the girl of picture 1 with the boy of picture 2, keeping picture 2’s background unchanged"  
-- For stylization tasks, describe the reference image’s style in the rewritten prompt, while preserving the visual content of the source image.  
-
-## 3. Rationale and Logic Check
-- Resolve contradictory instructions: e.g., “Remove all trees but keep all trees” requires logical correction.
-- Supplement missing critical information: e.g., if position is unspecified, choose a reasonable area based on composition (near subject, blank space, center/edge, etc.).
-
-# Output Format Example
-```json
-{
-   "Rewritten": "..."
-}
-'''
+def find_my_model(a_, b_):
+    if a_ is None or a_.endswith(".pth"):
+        return a_, b_
+
+    txt_files = []
+    for base_file in [a_, b_]:
+        if base_file is not None and base_file.endswith(".txt"):
+            txt_files.append(base_file)
+
+    directory = os.path.dirname(a_)
+
+    for txt in txt_files:
+        with open(txt, 'r') as file:
+            first_line = file.readline()
+
+        download_manager(
+            url=first_line.strip(),
+            path=directory,
+            extension="",
+        )
+
+    for f in find_files(directory):
+        if f.endswith(".zip"):
+            unzip_in_folder(f, directory)
+
+    model = None
+    index = None
+    end_files = find_files(directory)
+
+    for ff in end_files:
+        if ff.endswith(".pth"):
+            model = os.path.join(directory, ff)
+            gr.Info(f"Model found: {ff}")
+        if ff.endswith(".index"):
+            index = os.path.join(directory, ff)
+            gr.Info(f"Index found: {ff}")
+
+    if not model:
+        gr.Error(f"Model not found in: {end_files}")
+
+    if not index:
+        gr.Warning("Index not found")
+
+    return model, index
+
+
+def ensure_valid_file(url):
+    if "huggingface" not in url:
+        raise ValueError("Only downloads from Hugging Face are allowed")
+
+    try:
+        request = urllib.request.Request(url, method="HEAD")
+        with urllib.request.urlopen(request) as response:
+            content_length = response.headers.get("Content-Length")
+
+        if content_length is None:
+            raise ValueError("No Content-Length header found")
+
+        file_size = int(content_length)
+        if file_size > 900000000 and IS_ZERO_GPU:
+            raise ValueError("The file is too large. Max allowed is 900 MB.")
+
+        return file_size
+
+    except Exception as e:
+        raise e
+
+
+def clear_files(directory):
+    time.sleep(15)
+    print(f"Clearing files: {directory}.")
+    shutil.rmtree(directory)
+
+
+# ✅ تابع کاملاً اصلاح شده — بدون خطای سینتکسی
+def get_my_model(url_data, progress=gr.Progress(track_tqdm=True)):
+    if not url_data:  # ⬅️ اصلاح شده: url_data + :
+        return None, None
+
+    if "," in url_data:  # ⬅️ اصلاح شده: url_data + :
+        a_, b_ = url_data.split(",")
+        a_, b_ = a_.strip().replace("/blob/", "/resolve/"), b_.strip().replace("/blob/", "/resolve/")
+    else:
+        a_, b_ = url_data.strip().replace("/blob/", "/resolve/"), None
+
+    out_dir = "downloads"
+    folder_download = str(random.randint(1000, 9999))
+    directory = os.path.join(out_dir, folder_download)
+    os.makedirs(directory, exist_ok=True)
+
+    try:
+        valid_url = [a_] if not b_ else [a_, b_]
+        for link in valid_url:
+            ensure_valid_file(link)
+            download_manager(
+                url=link,
+                path=directory,
+                extension="",
+            )
+
+        for f in find_files(directory):
+            if f.endswith(".zip"):
+                unzip_in_folder(f, directory)
+
+        model = None
+        index = None
+        end_files = find_files(directory)
+
+        for ff in end_files:
+            if ff.endswith(".pth"):
+                model = ff
+                gr.Info(f"Model found: {ff}")
+            if ff.endswith(".index"):
+                index = ff
+                gr.Info(f"Index found: {ff}")
+
+        if not model:
+            raise ValueError(f"Model not found in: {end_files}")
+
+        if not index:
+            gr.Warning("Index not found")
+        else:
+            index = os.path.abspath(index)
+
+        return os.path.abspath(model), index
+
+    except Exception as e:
+        raise e
+    finally:
+        t = threading.Thread(target=clear_files, args=(directory,))
+        t.start()
 
-def polish_prompt(prompt, img):
-    prompt = f"{SYSTEM_PROMPT}\n\nUser Input: {prompt}\n\nRewritten Prompt:"
-    success=False
-    while not success:
+
+def add_audio_effects(audio_list, type_output):
+    print("Audio effects")
+
+    result = []
+    for audio_path in audio_list:
         try:
-            result = api(prompt, [img])
-            # print(f"Result: {result}")
-            # print(f"Polished Prompt: {polished_prompt}")
-            if isinstance(result, str):
-                result = result.replace('```json','')
-                result = result.replace('```','')
-                result = json.loads(result)
-            else:
-                result = json.loads(result)
-
-            polished_prompt = result['Rewritten']
-            polished_prompt = polished_prompt.strip()
-            polished_prompt = polished_prompt.replace("\n", " ")
-            success = True
+            output_path = f'{os.path.splitext(audio_path)[0]}_effects.{type_output}'
+
+            board = Pedalboard(
+                [
+                    HighpassFilter(),
+                    Compressor(ratio=4, threshold_db=-15),
+                    Reverb(room_size=0.10, dry_level=0.8, wet_level=0.2, damping=0.7)
+                 ]
+            )
+
+            temp_wav = f'{os.path.splitext(audio_path)[0]}_temp.wav'
+
+            with AudioFile(audio_path) as f:
+                with AudioFile(temp_wav, 'w', f.samplerate, f.num_channels) as o:
+                    while f.tell() < f.frames:
+                        chunk = f.read(int(f.samplerate))
+                        effected = board(chunk, f.samplerate, reset=False)
+                        o.write(effected)
+
+            audio_seg = AudioSegment.from_file(temp_wav, format=type_output)
+            audio_seg.export(output_path, format=type_output, bitrate=("320k" if type_output == "mp3" else None))
+
+            os.remove(temp_wav)
+
+            result.append(output_path)
         except Exception as e:
-            print(f"[Warning] Error during API call: {e}")
-    return polished_prompt
-
-
-def encode_image(pil_image):
-    import io
-    buffered = io.BytesIO()
-    pil_image.save(buffered, format="PNG")
-    return base64.b64encode(buffered.getvalue()).decode("utf-8")
-
-
-
-
-def api(prompt, img_list, model="qwen-vl-max-latest", kwargs={}):
-    import dashscope
-    api_key = os.environ.get('DASH_API_KEY')
-    if not api_key:
-        raise EnvironmentError("DASH_API_KEY is not set")
-    assert model in ["qwen-vl-max-latest"], f"Not implemented model {model}"
-    sys_promot = "you are a helpful assistant, you should provide useful answers to users."
-    messages = [
-        {"role": "system", "content": sys_promot},
-        {"role": "user", "content": []}]
-    for img in img_list:
-        messages[1]["content"].append(
-            {"image": f"data:image/png;base64,{encode_image(img)}"})
-    messages[1]["content"].append({"text": f"{prompt}"})
-
-    response_format = kwargs.get('response_format', None)
-
-    response = dashscope.MultiModalConversation.call(
-        api_key=api_key,
-        model=model, # For example, use qwen-plus here. You can change the model name as needed. Model list: https://help.aliyun.com/zh/model-studio/getting-started/models
-        messages=messages,
-        result_format='message',
-        response_format=response_format,
+            traceback.print_exc()
+            print(f"Error audio effects: {str(e)}")
+            result.append(audio_path)
+
+    return result
+
+
+def apply_noisereduce(audio_list, type_output):
+    print("Noise reduce")
+
+    result = []
+    for audio_path in audio_list:
+        out_path = f"{os.path.splitext(audio_path)[0]}_noisereduce.{type_output}"
+
+        try:
+            audio = AudioSegment.from_file(audio_path)
+            samples = np.array(audio.get_array_of_samples())
+            reduced_noise = nr.reduce_noise(samples, sr=audio.frame_rate, prop_decrease=0.6)
+
+            reduced_audio = AudioSegment(
+                reduced_noise.tobytes(), 
+                frame_rate=audio.frame_rate, 
+                sample_width=audio.sample_width,
+                channels=audio.channels
+            )
+
+            reduced_audio.export(out_path, format=type_output, bitrate=("320k" if type_output == "mp3" else None))
+            result.append(out_path)
+
+        except Exception as e:
+            traceback.print_exc()
+            print(f"Error noisereduce: {str(e)}")
+            result.append(audio_path)
+
+    return result
+
+
+@spaces.GPU()
+def convert_now(audio_files, random_tag, converter, type_output, steps):
+    for step in range(steps):
+        audio_files = converter(
+            audio_files,
+            random_tag,
+            overwrite=False,
+            parallel_workers=(2 if IS_COLAB else 8),
+            type_output=type_output,
         )
 
-    if response.status_code == 200:
-        return response.output.choices[0].message.content[0]['text']
-    else:
-        raise Exception(f'Failed to post: {response}')
-
-# --- Model Loading ---
-dtype = torch.bfloat16
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-# Load the model pipeline
-pipe = QwenImageEditPlusPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2509", torch_dtype=dtype).to(device)
-
-# --- UI Constants and Helpers ---
-MAX_SEED = np.iinfo(np.int32).max
-
-# --- Main Inference Function (with hardcoded negative prompt) ---
-@spaces.GPU(duration=300)
-def infer(
-    images,
-    prompt,
-    seed=42,
-    randomize_seed=False,
-    true_guidance_scale=1.0,
-    num_inference_steps=50,
-    height=None,
-    width=None,
-    rewrite_prompt=True,
-    num_images_per_prompt=1,
-    progress=gr.Progress(track_tqdm=True),
+    return audio_files
+
+
+def run(
+    audio_files,
+    file_m,
+    pitch_alg,
+    pitch_lvl,
+    file_index,
+    index_inf,
+    r_m_f,
+    e_r,
+    c_b_p,
+    active_noise_reduce,
+    audio_effects,
+    type_output,
+    steps,
 ):
-    """
-    Generates an image using the local Qwen-Image diffusers pipeline.
-    """
-    # Hardcode the negative prompt as requested
-    negative_prompt = " "
-    
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
+    if not audio_files:
+        raise ValueError("Please upload audio files")
+
+    if isinstance(audio_files, str):
+        audio_files = [audio_files]
+
+    try:
+        duration_base = librosa.get_duration(filename=audio_files[0])
+        print("Duration:", duration_base)
+    except Exception as e:
+        print(e)
+
+    if file_m is not None and file_m.endswith(".txt"):
+        file_m, file_index = find_my_model(file_m, file_index)
+        print(file_m, file_index)
+
+    random_tag = "USER_"+str(random.randint(10000000, 99999999))
+
+    converter.apply_conf(
+        tag=random_tag,
+        file_model=file_m,
+        pitch_algo=pitch_alg,
+        pitch_lvl=pitch_lvl,
+        file_index=file_index,
+        index_influence=index_inf,
+        respiration_median_filtering=r_m_f,
+        envelope_ratio=e_r,
+        consonant_breath_protection=c_b_p,
+        resample_sr=0,  # ⬅️ مهم: بدون ری‌سمپل برای کیفیت بالاتر
+    )
+    time.sleep(0.1)
 
-    # Set up the generator for reproducibility
-    generator = torch.Generator(device=device).manual_seed(seed)
-    
-    # Load input images into PIL Images
-    pil_images = []
-    if images is not None:
-        for item in images:
-            try:
-                if isinstance(item[0], Image.Image):
-                    pil_images.append(item[0].convert("RGB"))
-                elif isinstance(item[0], str):
-                    pil_images.append(Image.open(item[0]).convert("RGB"))
-                elif hasattr(item, "name"):
-                    pil_images.append(Image.open(item.name).convert("RGB"))
-            except Exception:
-                continue
+    result = convert_now(audio_files, random_tag, converter, type_output, steps)
+
+    if active_noise_reduce:
+        result = apply_noisereduce(result, type_output)
+
+    if audio_effects:
+        result = add_audio_effects(result, type_output)
+
+    return result
+
+
+def audio_conf():
+    return gr.File(
+        label="Upload Audio Files (wav, mp3, ogg, flac)",
+        file_count="multiple",
+        type="filepath",
+        file_types=[".wav", ".mp3", ".ogg", ".flac", ".m4a"],
+        container=True,
+    )
+
+
+def model_conf():
+    return gr.File(
+        label="Upload Model File (.pth)",
+        type="filepath",
+        file_types=[".pth"],
+        height=130,
+    )
+
+
+def pitch_algo_conf():
+    return gr.Dropdown(
+        PITCH_ALGO_OPT,
+        value="rmvpe+",  # ⬅️ بهترین الگوریتم برای کیفیت
+        label="Pitch Algorithm (rmvpe+ recommended)",
+        visible=True,
+        interactive=True,
+    )
+
+
+def pitch_lvl_conf():
+    return gr.Slider(
+        label="Pitch Shift (نازک/کلفت کردن صدا)",
+        minimum=-24,
+        maximum=24,
+        step=1,
+        value=0,
+        visible=True,
+        interactive=True,
+        info="🔹 مثبت = نازک‌تر (مثل کارتون) | منفی = کلفت‌تر (مثل غول)"
+    )
+
+
+def index_conf():
+    return gr.File(
+        label="Upload Index File (.index) - Optional (Recommended for Quality!)",
+        type="filepath",
+        file_types=[".index"],
+        height=130,
+    )
 
-    if height==256 and width==256:
-        height, width = None, None
-    print(f"Calling pipeline with prompt: '{prompt}'")
-    print(f"Negative Prompt: '{negative_prompt}'")
-    print(f"Seed: {seed}, Steps: {num_inference_steps}, Guidance: {true_guidance_scale}, Size: {width}x{height}")
-    if rewrite_prompt and len(pil_images) > 0:
-        prompt = polish_prompt(prompt, pil_images[0])
-        print(f"Rewritten Prompt: {prompt}")
-    
 
-    # Generate the image
-    image = pipe(
-        image=pil_images if len(pil_images) > 0 else None,
-        prompt=prompt,
-        height=height,
-        width=width,
-        negative_prompt=negative_prompt,
-        num_inference_steps=num_inference_steps,
-        generator=generator,
-        true_cfg_scale=true_guidance_scale,
-        num_images_per_prompt=num_images_per_prompt,
-    ).images
-
-    return image, seed
-
-# --- Examples and UI Layout ---
-examples = []
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 1024px;
+def index_inf_conf():
+    return gr.Slider(
+        minimum=0,
+        maximum=1,
+        label="Index Influence (Higher = More Detail)",
+        value=0.9,  # ⬅️ بهینه برای کیفیت
+    )
+
+
+def respiration_filter_conf():
+    return gr.Slider(
+        minimum=0,
+        maximum=7,
+        label="Respiration Median Filtering",
+        value=3,
+        step=1,
+        interactive=True,
+    )
+
+
+def envelope_ratio_conf():
+    return gr.Slider(
+        minimum=0,
+        maximum=1,
+        label="Envelope Ratio (Controls Dynamics)",
+        value=0.5,  # ⬅️ بهینه برای طبیعی‌بودن
+        interactive=True,
+    )
+
+
+def consonant_protec_conf():
+    return gr.Slider(
+        minimum=0,
+        maximum=0.5,
+        label="Consonant Breath Protection",
+        value=0.3,  # ⬅️ کاهش برای جلوگیری از مصنوعی شدن
+        interactive=True,
+    )
+
+
+def button_conf():
+    return gr.Button(
+        "Convert Voice (High Quality Mode)",
+        variant="primary",
+        size="lg",
+    )
+
+
+def output_conf():
+    return gr.File(
+        label="Converted Audio (High Quality Output)",
+        file_count="multiple",
+        interactive=False,
+    )
+
+
+def active_tts_conf():
+    return gr.Checkbox(
+        False,
+        label="Use Text-to-Speech",
+        container=False,
+    )
+
+
+def tts_voice_conf():
+    return gr.Dropdown(
+        label="TTS Voice",
+        choices=[],  # Will be populated later
+        visible=False,
+        value=None,
+    )
+
+
+def tts_text_conf():
+    return gr.Textbox(
+        value="",
+        placeholder="Enter text to convert to speech...",
+        label="Text",
+        visible=False,
+        lines=3,
+    )
+
+
+def tts_button_conf():
+    return gr.Button(
+        "Generate Speech",
+        variant="secondary",
+        visible=False,
+    )
+
+
+def tts_play_conf():
+    return gr.Checkbox(
+        False,
+        label="Auto-play generated audio",
+        container=False,
+        visible=False,
+    )
+
+
+def sound_gui():
+    return gr.Audio(
+        value=None,
+        type="filepath",
+        autoplay=True,
+        visible=True,
+        interactive=False,
+        elem_id="audio_tts",
+    )
+
+
+def steps_conf():
+    return gr.Slider(
+        minimum=1,
+        maximum=3,
+        label="Conversion Steps (1 recommended for speed & quality)",
+        value=1,
+        step=1,
+        interactive=True,
+    )
+
+
+def format_output_gui():
+    return gr.Dropdown(
+        label="Output Format (WAV for Best Quality)",
+        choices=["wav", "flac", "mp3"],
+        value="wav",  # ⬅️ فرمت بدون فشرده‌سازی
+    )
+
+
+def denoise_conf():
+    return gr.Checkbox(
+        False,  # ⬅️ پیش‌فرض غیرفعال — فقط در صورت نیاز فعال شود
+        label="Apply Noise Reduction (May reduce quality)",
+        container=False,
+        visible=True,
+    )
+
+
+def effects_conf():
+    return gr.Checkbox(
+        False,  # ⬅️ پیش‌فرض غیرفعال
+        label="Apply Audio Effects (Reverb) (May reduce clarity)",
+        container=False,
+        visible=True,
+    )
+
+
+def infer_tts_audio(tts_voice, tts_text, play_tts):
+    out_dir = "output"
+    folder_tts = "USER_"+str(random.randint(10000, 99999))
+
+    os.makedirs(out_dir, exist_ok=True)
+    os.makedirs(os.path.join(out_dir, folder_tts), exist_ok=True)
+    out_path = os.path.join(out_dir, folder_tts, "tts.mp3")
+
+    # Extract ShortName from combined value (e.g., "en-US-EmmaMultilingualNeural-Female")
+    if tts_voice:
+        short_name = "-".join(tts_voice.split('-')[:-1])
+    else:
+        short_name = "en-US-EmmaMultilingualNeural"
+
+    asyncio.run(edge_tts.Communicate(tts_text, short_name).save(out_path))
+    if play_tts:
+        return [out_path], out_path
+    return [out_path], None
+
+
+def show_components_tts(value_active):
+    return gr.update(
+        visible=value_active
+    ), gr.update(
+        visible=value_active
+    ), gr.update(
+        visible=value_active
+    ), gr.update(
+        visible=value_active
+    )
+
+
+def down_active_conf():
+    return gr.Checkbox(
+        False,
+        label="Download from URL",
+        container=False,
+    )
+
+
+def down_url_conf():
+    return gr.Textbox(
+        value="",
+        placeholder="Hugging Face model URL...",
+        label="Model URL",
+        visible=False,
+        lines=1,
+    )
+
+
+def down_button_conf():
+    return gr.Button(
+        "Download Model",
+        variant="secondary",
+        visible=False,
+    )
+
+
+def show_components_down(value_active):
+    return gr.update(
+        visible=value_active
+    ), gr.update(
+        visible=value_active
+    ), gr.update(
+        visible=value_active
+    )
+
+CSS = """
+#audio_tts {
+  visibility: hidden;
+  height: 0px;
+  width: 0px;
+  max-width: 0px;
+  max-height: 0px;
 }
-#edit_text{margin-top: -62px !important}
 """
 
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.HTML('<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/qwen_image_edit_logo.png" alt="Qwen-Image Logo" width="400" style="display: block; margin: 0 auto;">')
-        gr.Markdown("[Learn more](https://github.com/QwenLM/Qwen-Image) about the Qwen-Image series. Try on [Qwen Chat](https://chat.qwen.ai/), or [download model](https://huggingface.co/Qwen/Qwen-Image-Edit) to run locally with ComfyUI or diffusers.")
-        with gr.Row():
-            with gr.Column():
-                input_images = gr.Gallery(label="Input Images", show_label=False, type="pil", interactive=True)
-
-            # result = gr.Image(label="Result", show_label=False, type="pil")
-            result = gr.Gallery(label="Result", show_label=False, type="pil")
-        with gr.Row():
-            prompt = gr.Text(
-                    label="Prompt",
-                    show_label=False,
-                    placeholder="describe the edit instruction",
-                    container=False,
+def get_gui(theme):
+    with gr.Blocks(theme=theme, css=CSS, fill_width=True, fill_height=False, delete_cache=delete_cache_time) as app:
+        gr.Markdown(title)
+        gr.Markdown(description)
+
+        with gr.Tab("Voice Conversion"):
+            # بخش آپلود فایل‌های صوتی
+            gr.Markdown("### 📤 Upload Audio Files")
+            aud = audio_conf()
+            
+            # بخش TTS
+            active_tts = active_tts_conf()
+            with gr.Row(visible=False) as tts_row:
+                with gr.Column(scale=1):
+                    tts_text = tts_text_conf()
+                with gr.Column(scale=2):
+                    with gr.Row():
+                        with gr.Column():
+                            with gr.Row():
+                                tts_voice = tts_voice_conf()
+                                tts_active_play = tts_play_conf()
+                    tts_button = tts_button_conf()
+                    tts_play = sound_gui()
+
+            active_tts.change(
+                fn=show_components_tts,
+                inputs=[active_tts],
+                outputs=[tts_voice, tts_text, tts_button, tts_active_play],
             )
-            run_button = gr.Button("Edit!", variant="primary")
-
-        with gr.Accordion("Advanced Settings", open=False):
-            # Negative prompt UI element is removed here
 
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
+            tts_button.click(
+                fn=infer_tts_audio,
+                inputs=[tts_voice, tts_text, tts_active_play],
+                outputs=[aud, tts_play],
             )
 
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
+            # بخش مدل
+            gr.Markdown("### 🎯 Model Selection")
+            
             with gr.Row():
+                with gr.Column(scale=1):
+                    model = model_conf()
+                    gr.Markdown("*Upload your .pth model file*")
+                with gr.Column(scale=1):
+                    indx = index_conf()
+                    gr.Markdown("*Upload .index file for best quality!*")
+
+            # بخش دانلود از URL
+            down_active_gui = down_active_conf()
+            down_info = gr.Markdown(
+                f"Download models from Hugging Face URLs",
+                visible=False
+            )
+            with gr.Row(visible=False) as url_row:
+                with gr.Column(scale=3):
+                    down_url_gui = down_url_conf()
+                with gr.Column(scale=1):
+                    down_button_gui = down_button_conf()
+
+            down_active_gui.change(
+                show_components_down,
+                [down_active_gui],
+                [down_info, down_url_gui, down_button_gui]
+            )
 
-                true_guidance_scale = gr.Slider(
-                    label="True guidance scale",
-                    minimum=1.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=4.0
-                )
+            down_button_gui.click(
+                get_my_model,
+                [down_url_gui],
+                [model, indx]
+            )
 
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=40,
-                )
-                
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=2048,
-                    step=8,
-                    value=None,
-                )
+            # تنظیمات پیشرفته
+            with gr.Accordion(label="⚙️ Advanced Settings (Optimized for Quality)", open=True):
+                with gr.Row():
+                    algo = pitch_algo_conf()
+                    algo_lvl = pitch_lvl_conf()
                 
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=2048,
-                    step=8,
-                    value=None,
-                )
+                with gr.Row():
+                    indx_inf = index_inf_conf()
+                    steps_gui = steps_conf()
                 
+                with gr.Row():
+                    res_fc = respiration_filter_conf()
+                    envel_r = envelope_ratio_conf()
+                    const = consonant_protec_conf()
                 
-                rewrite_prompt = gr.Checkbox(label="Rewrite prompt", value=False)
-
-        # gr.Examples(examples=examples, inputs=[prompt], outputs=[result, seed], fn=infer, cache_examples=False)
-
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            input_images,
-            prompt,
-            seed,
-            randomize_seed,
-            true_guidance_scale,
-            num_inference_steps,
-            height,
-            width,
-            rewrite_prompt,
-        ],
-        outputs=[result, seed],
-    )
+                with gr.Row():
+                    format_out = format_output_gui()
+                    denoise_gui = denoise_conf()
+                    effects_gui = effects_conf()
+
+            # دکمه تبدیل
+            button_base = button_conf()
+            
+            # نتیجه
+            gr.Markdown("### 🎵 Output (High Quality)")
+            output_base = output_conf()
+
+            button_base.click(
+                run,
+                inputs=[
+                    aud,
+                    model,
+                    algo,
+                    algo_lvl,
+                    indx,
+                    indx_inf,
+                    res_fc,
+                    envel_r,
+                    const,
+                    denoise_gui,
+                    effects_gui,
+                    format_out,
+                    steps_gui,
+                ],
+                outputs=[output_base],
+            )
+
+        gr.Markdown(RESOURCES)
+
+    return app
+
 
 if __name__ == "__main__":
-    demo.launch()
+    # Get voice list safely
+    tts_voice_list = asyncio.new_event_loop().run_until_complete(get_voices_list(proxy=None))
+    
+    # Build voice dropdown options with safe .get() access
+    voices = sorted([
+        (
+            " - ".join(
+                reversed(
+                    voice.get("FriendlyName", voice.get("Name", "Unknown Voice")).split("-")
+                )
+            ).replace("Microsoft ", "").replace("Online (Natural)", f"({voice.get('Gender', 'Unknown')})").strip(),
+            f"{voice.get('ShortName', 'Unknown')}-{voice.get('Gender', 'Unknown')}"
+        )
+        for voice in tts_voice_list
+    ])
+
+    # Initialize GUI
+    app = get_gui(theme)
+    app.queue(default_concurrency_limit=40)
+
+    # Launch app
+    app.launch(
+        max_threads=40,
+        share=IS_COLAB,
+        show_error=True,
+        quiet=False,
+        debug=IS_COLAB,
+        ssr_mode=False,
+    )