接上篇语音转文字以及智能对话链接http://t.csdnimg.cn/LA0Lb
以下代码实现文字转语音并且转化为可播放的wav的格式并且播报python代码
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
import subprocess
import pygame
import platform
import wave
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
counter = 0 # 定义全局变量 counter
# 创建一个全局变量来存储音频数据
audio_data = b''
class Ws_Param(object):
# 初始化
def __init__(self, APPID, APIKey, APISecret, Text, save_folder):
self.APPID = APPID
self.APIKey = APIKey
self.APISecret = APISecret
self.Text = Text
self.save_folder = save_folder
# 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": "xiaoyan", "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)
return url
def on_message(ws, message):
global audio_data # 声明我们要使用全局变量 audio_data
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:
# 将接收到的音频数据添加到 audio_data
audio_data += audio
if status == 2: # 如果接收到表示音频结束的消息
# 生成唯一的文件名
filename = "output" + str(counter) + ".pcm"
file_path = os.path.join(wsParam.save_folder, filename)
with open(file_path, 'wb') as f:
f.write(audio_data) # 将所有音频数据写入文件
# 保存音频文件
save_as_wav(file_path)
# 播放文件
audio_data = b'' # 清空 audio_data 以便于下一次使用
except Exception as e:
print("receive msg, but parse exception:", e)
def play_audio(file_path):
# 初始化 pygame
pygame.mixer.init()
# 加载音频文件
pygame.mixer.music.load(file_path)
# 播放音频文件
pygame.mixer.music.play()
# 等待音频播放完毕
while pygame.mixer.music.get_busy():
pygame.time.Clock().tick(10)
def save_as_wav(file_path):
# 将 PCM 格式的音频转换为 WAV 格式
pcm_path = file_path
wav_path = os.path.splitext(file_path)[0] + '.wav'
with wave.open(wav_path, 'wb') as wf:
wf.setnchannels(1)
wf.setsampwidth(2)
wf.setframerate(16000)
with open(pcm_path, 'rb') as pcmf:
data = pcmf.read()
wf.writeframes(data)
play_audio(wav_path)
# 收到websocket错误的处理
def on_error(ws, error):
print("### error:", error)
# 收到websocket关闭的处理
def on_close(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)
thread.start_new_thread(run, ())
def text_to_speech(text, save_folder):
global wsParam # 声明我们要使用全局变量 wsParam
# 使用讯飞的语音合成 API
print("hello")
if not isinstance(text, str) or not text:
print("Error: text 参数必须是一个非空的字符串")
return
# 使用讯飞的语音合成 API
wsParam = Ws_Param(APPID='a54e918d', APISecret='YjU5MjYwZmNmODM0YmM5ODA2MmI3YmNl',
APIKey='a0da0eb117e75c5b24dee425178f311d',
Text=text,
save_folder=save_folder)
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})
if __name__ == "__main__":
# 指定保存音频文件的文件夹
save_folder = r"C:\Usxxxxxxxxxxx"
# 测试时候在此处正确填写相关信息即可运行
wsParam = Ws_Param(APPID='a54e918d', APISecret='YjU5MjYwZmNmODM0YmM5ODxxxxxxNl',
APIKey='a0da0eb117e75c5b24dxxxxxx',
Text="这是一个语音合成示例1111111111",
save_folder=save_folder)
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})