使用科大讯飞API进行语音识别和合成代码

以下是使用科大讯飞API进行语音识别和合成的Python代码示例：

语音识别：

import requests
import json

url = "http://api.xfyun.cn/v1/service/v1/iat"
APPID = "YOUR_APPID"  # 替换为自己的APPID
API_KEY = "YOUR_API_KEY"  # 替换为自己的API_KEY

audio_file = "test.wav"  # 需要识别的音频文件路径
with open(audio_file, "rb") as f:
    audio_data = f.read()
    
param = {
    "engine_type": "sms16k",  # 引擎类型，此处使用16k采样率的普通话识别
    "aue": "raw",  # 音频编码格式，此处为未压缩的音频数据
}

headers = {
    "Content-Type": "application/x-www-form-urlencoded; charset=utf-8",
    "X-Appid": APPID,
    "X-CurTime": str(int(time.time())),
    "X-Param": base64.b64encode(json.dumps(param).replace(' ', '').encode('utf-8')).decode('utf-8'),
    "X-CheckSum": hashlib.md5((API_KEY + str(int(time.time())) + base64.b64encode(audio_data).decode('utf-8')) \
                              .encode('utf-8')).hexdigest(),
}

response = requests.post(url, headers=headers, data=audio_data)
result = json.loads(response.text)
if result["code"] == "0":
    print("识别结果：", result["data"])
else:
    print("识别失败：", result["desc"])

语音合成：

import requests
import json
import time
import hashlib
import base64

url = "http://api.xfyun.cn/v1/service/v1/tts"
APPID = "YOUR_APPID"  # 替换为自己的APPID
API_KEY = "YOUR_API_KEY"  # 替换为自己的API_KEY

text = "科大讯飞提供全球领先的人工智能技术、产品和服务，致力于让机器具备智能的思维和感官能力。"  # 需要合成的文本内容
param = {
    "auf": "audio/L16;rate=16000",  # 音频采样率和编码格式
    "aue": "lame",  # 音频编码格式，此处使用mp3
    "voice_name": "xiaoyan",  # 合成的发音人
    "speed": "50",  # 合成语速
    "volume": "50",  # 合成音量
    "pitch": "50",  # 合成音调
    "engine_type": "intp65",  # 引擎类型
    "text": text,  # 合成的文本内容
}

headers = {
    "Content-Type": "application/x-www-form-urlencoded; charset=utf-8",
    "X-Appid": APPID,
    "X-CurTime": str(int(time.time())),
    "X-Param": base64.b64encode(json.dumps(param).replace(' ', '').encode('utf-8')).decode('utf-8'),
    "X-CheckSum": hashlib.md5((API_KEY + str(int(time.time())) + base64.b64encode(text.encode('utf-8')).decode('utf-8')) \
                              .encode('utf-8')).hexdigest(),
}

response = requests.post(url, headers=headers)
result = json.loads(response.text)
if result["code"] == "0":
    audio_data = base64.b64decode(result["data"])
    audio_file = "output.mp3"  # 合成的音频保存路径
    with open(audio_file, "wb") as f:
        f.write(audio_data)
    print("合成成功，音频文件保存在：", audio_file)
else:
    print("合成失败：", result["desc"])