阿里云语音合成

开通用户可享有所有支持试用的产品免费试用3个月

获取：OKEN="yourToken"

获取：APPKEY="yourAppkey"

阿里云语音合成接口说明

import os
import nls.speech_synthesizer
import random

URL = "wss://nls-gateway-cn-shanghai.aliyuncs.com/ws/v1"
TOKEN="yourToken" 
APPKEY="yourAppkey"  

class MyTTS:

    def on_metainfo(self, message, *args):
        print("on_metainfo message=>{}".format(message))

    def on_error(self, message, *args):
        print("on_error args=>{}".format(args))

    def on_close(self, *args):
        print("on_close: args=>{}".format(args))
        try:
            self.__file.close()
            print(f"File {self.__file.name} closed successfully.")
        except Exception as e:
            print("close failed:", e)

    def on_data(self, data, *args):
        try:
            self.__file.write(data)
            print(f"Data written to {self.__file.name}.")
        except Exception as e:
            print("write data failed:", e)

    def on_completed(self, message, *args):
        print("on_completed:args=>{} message=>{}".format(args, message))
        try:
            self.__file.close()
            print(f"File {self.__file.name} closed successfully.")
        except Exception as e:
            print("close failed:", e)

    def run(self, text, voice, file):
        try:
            self.__file = open(file, "wb")
            self.__text = text
            self.__voice = voice
            tts = nls.NlsSpeechSynthesizer(
                url=URL,
                token=TOKEN,
                appkey=APPKEY,
                on_metainfo=self.on_metainfo,
                on_data=self.on_data,
                on_completed=self.on_completed,
                on_error=self.on_error,
                on_close=self.on_close
            )
            tts.start(self.__text, voice=self.__voice, aformat="mp3")
            print(f"Speech synthesis for voice '{self.__voice}' initiated.")
        except Exception as e:
            print(f"Failed to start TTS for voice '{voice}': {e}")

voice_list = [
    # Mixed Chinese and English
    "abin", "zhixiaobai", "zhixiaoxia", "zhixiaomei", "zhigui", "zhishuo", "aixia", "cally", 
    "zhifeng_emo", "zhibing_emo", "zhimiao_emo", "zhimi_emo", "zhiyan_emo", "zhibei_emo", 
    "zhitian_emo", "xiaoyun", "xiaogang", "ruoxi", "siqi", "sijia", "sicheng", "aiqi", 
    "aijia", "aicheng", "aida", "ninger", "ruilin", "siyue", "aiya", "aimei", "aiyu", 
    "aiyue", "aijing", "xiaomei", "ailun", "maoxiaomei", "mashu", "xiaoxian", 
    "aifei", "yaqun", "qiaowei", "dahu", "guijie", "stella", "stanley", "kenny", 
    "rosa", "chuangirl", "lydia", "aishuo",
    # Pure Chinese
    "aina", "yina", "sijing", "sitong", "xiaobei", "aitong", "aiwei", "aibao", 
    "zhimao", "yuer", "qingqing", "cuijie", "xiaoze", "aikan", "zhiyuan", "zhiya", 
    "zhiyue", "zhida", "zhistella", "jielidou", "laotie", "laomei",
    # Pure English
    "harry", "abby", "andy", "eric", "emily", "luna", "luca", "wendy", "annie", 
    "william", "olivia", "beth", "cindy", "donna", "eva", "brian", "becca", "ava",
    # Japanese
    "tomoka", "tomoya",
    # Indonesian
    "indah",
    # Cantonese, English, Chinese mixed
    "taozi", "jiajia", "shanshan",
    # Malay
    "farah",
    # Filipino
    "tala",
    # Vietnamese
    "tien",
    # Korean
    "Kyong",
    # Russian
    "masha",
    # Spanish
    "camila",
    # Italian
    "perla",
    # Hong Kong
    "kelly",
    # French
    "clara", "hanna",
    # German
    "waan",
    # Thai
    "betty"
]

synthesizer = MyTTS()

# Specify save directory
save_directory = r"F:\tts"
os.makedirs(save_directory, exist_ok=True)

# Read text from txt file and generate audio
txt_file = r"F:\tts\1.txt"

with open(txt_file, 'r', encoding='utf-8') as file:
    for line_number, text in enumerate(file, 1):
        if len(text.strip()) == 0:
            continue
        random_voice = random.choice(voice_list)
        file_path = os.path.join(save_directory, f"fake_ali{line_number}_{random_voice}.mp3")
        synthesizer.run(text=text.strip(), voice=random_voice, file=file_path)