59 lines
1.5 KiB
Python
59 lines
1.5 KiB
Python
|
"""
|
|||
|
|
TTS 服务：文字转语音
|
|||
|
|
"""
|
|||
|
|
import base64
|
|||
|
|
import os
|
|||
|
|
from io import BytesIO
|
|||
|
|
|
|||
|
|
from openai import OpenAI
|
|||
|
|
|
|||
|
|
|
|||
|
|
class TTSService:
|
|||
|
|
"""TTS 服务（文字转语音）"""
|
|||
|
|
|
|||
|
|
def __init__(self):
|
|||
|
|
api_key = os.getenv("OPENAI_API_KEY", "")
|
|||
|
|
if api_key:
|
|||
|
|
self.client = OpenAI(api_key=api_key)
|
|||
|
|
else:
|
|||
|
|
self.client = None
|
|||
|
|
|
|||
|
|
async def synthesize(self, text: str) -> str:
|
|||
|
|
"""
|
|||
|
|
将文字转换为语音
|
|||
|
|
|
|||
|
|
Args:
|
|||
|
|
text: 要转换的文字
|
|||
|
|
|
|||
|
|
Returns:
|
|||
|
|
Base64 编码的音频数据
|
|||
|
|
"""
|
|||
|
|
if not self.client:
|
|||
|
|
# 如果没有配置 API Key，返回空字符串
|
|||
|
|
return ""
|
|||
|
|
|
|||
|
|
try:
|
|||
|
|
# 调用 OpenAI TTS API
|
|||
|
|
response = self.client.audio.speech.create(
|
|||
|
|
model="tts-1",
|
|||
|
|
voice="alloy", # 可选: alloy, echo, fable, onyx, nova, shimmer
|
|||
|
|
input=text
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
# 读取音频数据
|
|||
|
|
audio_bytes = BytesIO()
|
|||
|
|
for chunk in response.iter_bytes():
|
|||
|
|
audio_bytes.write(chunk)
|
|||
|
|
|
|||
|
|
# 转换为 Base64
|
|||
|
|
audio_data = audio_bytes.getvalue()
|
|||
|
|
audio_base64 = base64.b64encode(audio_data).decode('utf-8')
|
|||
|
|
return audio_base64
|
|||
|
|
except Exception as e:
|
|||
|
|
# 出错时返回空字符串
|
|||
|
|
print(f"TTS 生成失败: {str(e)}")
|
|||
|
|
return ""
|
|||
|
|
|
|||
|
|
|
|||
|
|
# 全局实例
|
|||
|
|
tts_service = TTSService()
|