html语音合成text2audio讯飞,python讯飞语音合成

# -*- coding:utf-8 -*-

#

# author: iflytek

#

# 本demo测试时运行的环境为:Windows + Python3.7

# 本demo测试成功运行时所安装的第三方库及其版本如下:

# cffi==1.12.3

# gevent==1.4.0

# greenlet==0.4.15

# pycparser==2.19

# six==1.12.0

# websocket==0.2.1

# websocket-client==0.56.0

#

# 错误码链接:https://www.xfyun.cn/document/error-code (code返回错误码时必看)

# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #

import websocket

import datetime

import hashlib

import base64

import hmac

import json

from urllib.parse import urlencode

import time

import ssl

from wsgiref.handlers import format_date_time

from datetime import datetime

from time import mktime

import _thread as thread

import os

ws=None

STATUS_FIRST_FRAME = 0 # 第一帧的标识

STATUS_CONTINUE_FRAME = 1 # 中间帧标识

STATUS_LAST_FRAME = 2 # 最后一帧的标识

class Ws_Param(object):

# 初始化

def __init__(self, APPID, APIKey, APISecret, Text):

self.APPID = APPID

self.APIKey = APIKey

self.APISecret = APISecret

self.Text = Text

# 公共参数(common)

self.CommonArgs = {"app_id": self.APPID}

# 业务参数(business),更多个性化参数可在官网查看

self.BusinessArgs = {"aue": "raw",

"auf": "audio/L16;rate=16000",

"vcn": "aisjiuxu",

"tte": "utf8"}

self.Data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-8')), "UTF8")}

# 生成url

def create_url(self):

url = 'wss://tts-api.xfyun.cn/v2/tts'

# 生成RFC1123格式的时间戳

now = datetime.now()

date = format_date_time(mktime(now.timetuple()))

# 拼接字符串

signature_origin = "host: " + "ws-api.xfyun.cn" + "\n"

signature_origin += "date: " + date + "\n"

signature_origin += "GET " + "/v2/tts " + "HTTP/1.1"

# 进行hmac-sha256进行加密

signature_sha = hmac.new(self.APISecret.encode('utf-8'), signature_origin.encode('utf-8'),

digestmod=hashlib.sha256).digest()

signature_sha = base64.b64encode(signature_sha).decode(encoding='utf-8')

authorization_origin = "api_key=\"%s\", algorithm=\"%s\", headers=\"%s\", signature=\"%s\"" % (

self.APIKey, "hmac-sha256", "host date request-line", signature_sha)

authorization = base64.b64encode(authorization_origin.encode('utf-8')).decode(encoding='utf-8')

# 将请求的鉴权参数组合为字典

v = {

"authorization": authorization,

"date": date,

"host": "ws-api.xfyun.cn"

}

# 拼接鉴权参数,生成url

url = url + '?' + urlencode(v)

# print("date: ",date)

# print("v: ",v)

# 此处打印出建立连接时候的url,参考本demo的时候可取消上方打印的注释,比对相同参数时生成的url与自己代码生成的url是否一致

# print('websocket url :', url)

return url

def on_message(ws, message):

try:

message =json.loads(message)

code = message["code"]

sid = message["sid"]

audio = message["data"]["audio"]

audio = base64.b64decode(audio)

status = message["data"]["status"]

if status == 2:

print("ws is closed")

ws.close()

if code != 0:

errMsg = message["message"]

print("sid:%s call error:%s code is:%s" % (sid, errMsg, code))

else:

with open('./demo.pcm', 'ab') as f:

f.write(audio)

cmd='ffmpeg -y -f s16be -ac 1 -ar 16000 -acodec pcm_s16le -i demo.pcm new_mp3.mp3'

import subprocess

subprocess.run(cmd)

# if status==2:

# print("ws is closed******")

# ws.close()

except Exception as e:

print("receive msg,but parse exception:", e)

# 收到websocket错误的处理

def on_error(ws, error):

# import time

# time.sleep(2)

print("### error:",ws)

print("### error:", error)

# 收到websocket关闭的处理

def on_close(ws):

print(ws)

print("### closed ###")

# 收到websocket连接建立的处理

def on_open(ws):

def run(*args):

d = {"common": wsParam.CommonArgs,

"business": wsParam.BusinessArgs,

"data": wsParam.Data,

}

d = json.dumps(d)

print("------>开始发送文本数据")

ws.send(d)

if os.path.exists('./demo.pcm'):

os.remove('./demo.pcm')

# time.sleep(2)

# ws.close()

thread.start_new_thread(run, ())

# run()

if __name__ == "__main__":

# 测试时候在此处正确填写相关信息即可运行

wsParam = Ws_Param(APPID='....', APIKey='.....',

APISecret='.....',

Text="请到控制台添加试用或购买发音人,添加后即显示发音人参数值")

websocket.enableTrace(False)

wsUrl = wsParam.create_url()

ws = websocket.WebSocketApp(wsUrl,

on_message=on_message,

on_error=on_error,

on_close=on_close)

ws.on_open = on_open

ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})

# ws.close()

  • 0
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
语音合成API可以通过Python编程语言进行调用。以下是一个简单的示例代码: ```python import requests import base64 # API请求的URL url = "http://api.xfyun.cn/v1/service/v1/tts" # 应用ID和API Key app_id = "your_app_id" api_key = "your_api_key" # 请求头部信息 headers = { "Content-Type": "application/x-www-form-urlencoded; charset=utf-8", "X-Param": "ssml", "X-Appid": app_id, "X-CurTime": "当前时间戳", "X-CheckSum": "MD5(app_key + cur_time + 参数)" } # 请求参数 text = "需要合成的文本" body = { "text": text, "voice_name": "xiaoyan", "speed": "50", "volume": "50", "pitch": "50", "engine_type": "intp65", "auf": "audio/L16;rate=16000", "aue": "raw" } # 计算X-CheckSum的值 import hashlib import time cur_time = str(int(time.time())) param = base64.b64encode(str(body).encode('utf-8')) m = hashlib.md5() m.update((api_key + cur_time + str(param, 'utf-8')).encode('utf-8')) checksum = m.hexdigest() headers['X-CurTime'] = cur_time headers['X-CheckSum'] = checksum # 发送POST请求 r = requests.post(url, headers=headers, data=body) # 保存返回的语音文件 with open("output.wav", "wb") as f: f.write(r.content) ``` 在上面的代码中,需要替换`your_app_id`和`your_api_key`为自己的应用ID和API Key。`text`变量表示需要合成的文本内容。请求头部信息中的`X-Param`表示请求参数的格式,这里使用了SSML格式。请求参数中的`voice_name`表示朗读人物,`speed`表示语速,`volume`表示音量,`pitch`表示音高,`engine_type`表示语音合成引擎类型,`auf`表示返回的音频格式,`aue`表示音频编码格式。计算`X-CheckSum`值的代码使用了MD5算法,需要将API Key和当前时间戳拼接后进行加密。最后将API返回的语音文件保存在本地的`output.wav`文件中。

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值