用腾讯云语音合成（TTS）批量生成英语绘本的朗读音频

import os
import time
import json
import base64
import PyPDF2
import pytesseract
from pdf2image import convert_from_path
from tencentcloud.common import credential
from tencentcloud.common.profile.client_profile import ClientProfile
from tencentcloud.common.profile.http_profile import HttpProfile
from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException
from tencentcloud.tts.v20190823 import tts_client, models
import moviepy.editor as mp
# 腾讯云API的SecretId和SecretKey
SECRET_ID = "XXX"
SECRET_KEY = "XXX"
# 文件夹路径
PDF_FOLDER = "F:\\aivideo"
def extract_text_from_pdf(pdf_path):
try:
# 尝试使用PyPDF2读取PDF文本
with open(pdf_path, 'rb') as file:
reader = PyPDF2.PdfFileReader(file)
text = ""
for page_num in range(reader.numPages):
page = reader.getPage(page_num)
text += page.extract_text()
return text
except:
# 如果失败，使用pdf2image和pytesseract进行OCR
images = convert_from_path(pdf_path)
text = ""
for image in images:
text += pytesseract.image_to_string(image, lang='eng')
return text
def split_text(text, max_length=400):
words = text.split()
chunks = []
current_chunk = []
current_length = 0
for word in words:
if current_length + len(word) + 1 > max_length:
chunks.append(' '.join(current_chunk))
current_chunk = [word]
current_length = len(word)
else:
current_chunk.append(word)
current_length += len(word) + 1
if current_chunk:
chunks.append(' '.join(current_chunk))
return chunks
def create_tts_task(client, text):
try:
req = models.TextToVoiceRequest()
params = {
"Text": text,
"SessionId": str(int(time.time())),
"ModelType": 1,
"VoiceType": 101001, # 英语女声
"SampleRate": 16000
}
req.from_json_string(json.dumps(params))
resp = client.TextToVoice(req)
return resp.Audio
except TencentCloudSDKException as err:
print(f"Error creating TTS task: {err}")
return None
def save_audio_to_file(audio, file_path):
with open(file_path, 'wb') as f:
f.write(base64.b64decode(audio))
print(f"Audio saved to {file_path}")
def merge_audio_files(file_paths, output_path):
clips = [mp.AudioFileClip(f) for f in file_paths]
final_clip = mp.concatenate_audioclips(clips)
final_clip.write_audiofile(output_path, codec='mp3')
for f in file_paths:
os.remove(f)
print(f"Merged audio saved to {output_path}")
def main():
cred = credential.Credential(SECRET_ID, SECRET_KEY)
httpProfile = HttpProfile()
httpProfile.endpoint = "http://tts.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = tts_client.TtsClient(cred, "ap-guangzhou", clientProfile)
for filename in os.listdir(PDF_FOLDER):
if filename.endswith('.pdf'):
pdf_path = os.path.join(PDF_FOLDER, filename)
print(f"Processing {pdf_path}")
text = extract_text_from_pdf(pdf_path)
if text:
chunks = split_text(text)
audio_files = []
for i, chunk in enumerate(chunks):
audio = create_tts_task(client, chunk)
if audio:
temp_file_path = os.path.join(PDF_FOLDER, f"temp_{i}.mp3")
save_audio_to_file(audio, temp_file_path)
audio_files.append(temp_file_path)
if audio_files:
output_file_path = os.path.join(PDF_FOLDER, os.path.splitext(filename)[0] + '.mp3')
merge_audio_files(audio_files, output_file_path)
else:
print(f"No text extracted from {pdf_path}")
if __name__ == "__main__":
main()