app.py

import gradio as gr
import edge_tts
import asyncio
import tempfile
import os
from moviepy.editor import AudioFileClip, concatenate_audioclips

# 获取所有可用的语音
async def get_voices():
    voices = await edge_tts.list_voices()
    return {f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] for v in voices}

# 文字转语音功能
async def text_to_speech(text, voice, rate, pitch):
    if not text.strip():
        return None, gr.Warning("Please enter the 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

# 生成SRT文件
def generate_srt(words, audio_duration, fps=24):
    srt_path = os.path.join(tempfile.gettempdir(), "output_subtitles.srt")
    with open(srt_path, 'w', encoding='utf-8') as srt_file:
        # Split audio duration into segments for SRT
        segment_duration = audio_duration / len(words)  # Average duration per word
        current_time = 0
        
        for i, word in enumerate(words):
            start_time = current_time
            end_time = start_time + segment_duration
            
            # Convert to SRT format
            start_time_str = format_srt_time(start_time)
            end_time_str = format_srt_time(end_time)
            srt_file.write(f"{i + 1}\n{start_time_str} --> {end_time_str}\n{word}\n\n")
            
            current_time += segment_duration  # Update current time

    return srt_path

def format_srt_time(seconds):
    millis = int((seconds - int(seconds)) * 1000)
    seconds = int(seconds)
    minutes = seconds // 60
    hours = minutes // 60
    minutes %= 60
    seconds %= 60
    return f"{hours:02}:{minutes:02}:{seconds:02},{millis:03}"

# 文字转音频和SRT功能
async def text_to_audio_and_srt(text, voice, rate, pitch):
    # Generate audio for the entire text
    audio_path, warning = await text_to_speech(text, voice, rate, pitch)
    if warning:
        return None, None, warning

    audio_clip = AudioFileClip(audio_path)
    audio_duration = audio_clip.duration
    
    # Generate SRT file based on the entire text
    words = text.split()
    srt_path = generate_srt(words, audio_duration)

    return audio_path, srt_path, None

# Gradio接口函数
def tts_interface(text, voice, rate, pitch):
    audio_path, srt_path, warning = asyncio.run(text_to_audio_and_srt(text, voice, rate, pitch))
    return audio_path, srt_path, warning

# 创建Gradio应用
async def create_demo():
    voices = await get_voices()
    
    demo = gr.Interface(
        fn=tts_interface,
        inputs=[
            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="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.File(label="Generated SRT", file_count="single"),
            gr.Markdown(label="Warning", visible=False)
        ],
        title="Edge TTS Text to Speech with Subtitles",
        description="Convert text to speech and generate subtitles (SRT) using Microsoft Edge TTS.",
        analytics_enabled=False,
        allow_flagging=False,
    )
    
    return demo

# 运行应用
if __name__ == "__main__":
    demo = asyncio.run(create_demo())
    demo.launch()