[超拟人语音合成] 科大讯飞API的Python实现_科大讯飞python语音对话

最近大模型开始漫延到了语音通话的领域了。我每天晚上回家的路上都会用手机和ChatGPT语音对话聊天，这不仅能够放松心情，而且还能够练习英语口语。很早的时候ChatGPT就释放了ASR和TTS的接口，试用了一下，英语能力还不错。

但是想要中文的话，我个人还是建议使用科大讯飞的这个“超拟人语音合成”API，合成的语音不仅可以自然的发声，而且还经过了文本模型的润色，使得其更加口语化表达。但是，官方给的python代码似乎使用起来比较困难，无法做到开箱即用。

于是，我和ChatGPT联手，又编写了如下的Python代码供大家使用。

在运行前，需要安装以下三个依赖：

playsound==1.3.0
Requests==2.31.0
websocket_client==1.8.0
1
2
3

下面是完整的代码，直接复制粘贴就可以使用。当然，需要配合自己的appid，api_secret，api_key来使用。关于其中的参数，可以参见《超拟人语音合成接口说明》。

# coding: utf-8
import _thread as thread

import base64
import datetime
import hashlib
import hmac
import json
from urllib.parse import urlparse
import ssl
from datetime import datetime
from time import mktime
from urllib.parse import urlencode
from wsgiref.handlers import format_date_time
import websocket
import os

class Ws_Param(object):
    # 初始化
    def __init__(self, APPID, APIKey, APISecret, gpt_url):
        self.APPID = APPID
        self.APIKey = APIKey
        self.APISecret = APISecret
        self.host = urlparse(gpt_url).netloc
        self.path = urlparse(gpt_url).path
        self.gpt_url = gpt_url

    # 生成url
    def create_url(self):
        # 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: " + self.host + "\n"
        signature_origin += "date: " + date + "\n"
        signature_origin += "GET " + self.path + " 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 = base64.b64encode(signature_sha).decode(encoding='utf-8')

        authorization_origin = f'api_key="{self.APIKey}", algorithm="hmac-sha256", headers="host date request-line", signature="{signature_sha_base64}"'

        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": self.host
        }
        # 拼接鉴权参数，生成url
        url = self.gpt_url + '?' + urlencode(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
        return url


# 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, ws1, ws2):
    print("### closed ###")


# 收到websocket连接建立的处理
def on_open(ws):
    thread.start_new_thread(run, (ws,))


# 收到websocket消息的处理
def on_message(ws, message):
    message = json.loads(message)
    code = message['header']['code']
    if code != 0:
        print("### 请求出错： ", message)
    else:
        payload = message.get("payload")
        status = message['header']['status']
        if status == 2:
            print("### 合成完毕")
            ws.close()
        if payload and payload != "null":
            audio = payload.get("audio")
            if audio:
                audio = audio["audio"]
                with open(ws.save_file_name, 'ab') as f:
                    f.write(base64.b64decode(audio))


def run(ws, *args):
    body = {
        "header": {
            "app_id": ws.appid,
            "status": 0
        },
        "parameter": {
            "oral": {
                "spark_assist": 1,
                "oral_level": "mid"
            },
            "tts": {
                "vcn": ws.vcn,
                "speed": 50,
                "volume": 50,
                "pitch": 50,
                "bgs": 0,
                "reg": 0,
                "rdn": 0,
                "rhy": 0,
                "scn": 5,
                "version": 0,
                "L5SilLen": 0,
                "ParagraphSilLen": 0,
                "audio": {
                    "encoding": "lame",
                    "sample_rate": 16000,
                    "channels": 1,
                    "bit_depth": 16,
                    "frame_size": 0
                },
                "pybuf": {
                    "encoding": "utf8",
                    "compress": "raw",
                    "format": "plain"
                }
            }
        },
        "payload": {
            "text": {
                "encoding": "utf8",
                "compress": "raw",
                "format": "json",
                "status": 0,
                "seq": 0,
                "text": str(base64.b64encode(ws.text.encode('utf-8')), "UTF8")
            }
        }
    }

    ws.send(json.dumps(body))


def main(appid, api_secret, api_key, url, text, vcn, save_file_name):
    wsParam = Ws_Param(appid, api_key, api_secret, url)
    wsUrl = wsParam.create_url()
    ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close, on_open=on_open)
    websocket.enableTrace(False)
    ws.appid = appid
    ws.text = text
    ws.vcn = vcn
    ws.save_file_name = save_file_name
    if os.path.exists(ws.save_file_name):
        os.remove(ws.save_file_name)
    ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})


if __name__ == "__main__":
    main(
        appid="###",
        api_secret="###",
        api_key="###",
        url="wss://cbm01.cn-huabei-1.xf-yun.com/v1/private/medd90fec",
        # 待合成文本
        text="AI让世界更懂你！",
        # 发音人参数
        vcn="x4_lingxiaoxuan_oral",
        save_file_name="./test.mp3"
    )
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174