From 1545a9f262d99ac06792fcd7c21f7548defae671 Mon Sep 17 00:00:00 2001
From: lanvent <lanvent@qq.com>
Date: Sat, 1 Apr 2023 16:36:27 +0800
Subject: [PATCH] feat: support azure voice

---
 config.py                        | 10 +++--
 voice/azure/azure_voice.py       | 70 ++++++++++++++++++++++++++++++++
 voice/azure/config.json.template |  4 ++
 voice/voice_factory.py           |  3 ++
 4 files changed, 84 insertions(+), 3 deletions(-)
 create mode 100644 voice/azure/azure_voice.py
 create mode 100644 voice/azure/config.json.template

diff --git a/config.py b/config.py
index 008f447..7a734b3 100644
--- a/config.py
+++ b/config.py
@@ -47,16 +47,20 @@ available_setting = {
     "speech_recognition": False,  # 是否开启语音识别
     "group_speech_recognition": False,  # 是否开启群组语音识别
     "voice_reply_voice": False,  # 是否使用语音回复语音，需要设置对应语音合成引擎的api key
-    "voice_to_text": "openai",  # 语音识别引擎，支持openai,google
-    "text_to_voice": "baidu",  # 语音合成引擎，支持baidu,google,pytts(offline)
+    "voice_to_text": "openai",  # 语音识别引擎，支持openai,google,azure
+    "text_to_voice": "baidu",  # 语音合成引擎，支持baidu,google,pytts(offline),azure
 
-    # baidu api的配置， 使用百度语音识别和语音合成时需要
+    # baidu 语音api配置， 使用百度语音识别和语音合成时需要
     "baidu_app_id": "",
     "baidu_api_key": "",
     "baidu_secret_key": "",
     # 1536普通话(支持简单的英文识别) 1737英语 1637粤语 1837四川话 1936普通话远场
     "baidu_dev_pid": "1536",
 
+    # azure 语音api配置， 使用azure语音识别和语音合成时需要
+    "azure_voice_api_key": "",
+    "azure_voice_region": "japaneast",
+
     # 服务时间限制，目前支持itchat
     "chat_time_module": False,  # 是否开启服务时间限制
     "chat_start_time": "00:00",  # 服务开始时间
diff --git a/voice/azure/azure_voice.py b/voice/azure/azure_voice.py
new file mode 100644
index 0000000..f9baf2b
--- /dev/null
+++ b/voice/azure/azure_voice.py
@@ -0,0 +1,70 @@
+
+"""
+azure voice service
+"""
+import json
+import os
+import time
+import azure.cognitiveservices.speech as speechsdk
+from aip import AipSpeech
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from common.tmp_dir import TmpDir
+from voice.voice import Voice
+from voice.audio_convert import get_pcm_from_wav
+from config import conf
+"""
+Azure voice
+主目录设置文件中需填写azure_voice_api_key和azure_voice_region
+
+查看可用的 voice： https://speech.microsoft.com/portal/voicegallery
+
+"""
+
+class AzureVoice(Voice):
+
+    def __init__(self):
+        try:
+            curdir = os.path.dirname(__file__)
+            config_path = os.path.join(curdir, "config.json")
+            config = None
+            if not os.path.exists(config_path): #如果没有配置文件，创建本地配置文件
+                config = { "speech_synthesis_voice_name": "zh-CN-XiaoxiaoNeural", "speech_recognition_language": "zh-CN"}
+                with open(config_path, "w") as fw:
+                    json.dump(config, fw, indent=4)
+            else:
+                with open(config_path, "r") as fr:
+                    config = json.load(fr)
+            self.api_key = conf().get('azure_voice_api_key')
+            self.api_region = conf().get('azure_voice_region')
+            self.speech_config = speechsdk.SpeechConfig(subscription=self.api_key, region=self.api_region)
+            self.speech_config.speech_synthesis_voice_name = config["speech_synthesis_voice_name"]
+            self.speech_config.speech_recognition_language = config["speech_recognition_language"]
+        except Exception as e:
+            logger.warn("AzureVoice init failed: %s, ignore " % e)
+
+    def voiceToText(self, voice_file):
+        audio_config = speechsdk.AudioConfig(filename=voice_file)
+        speech_recognizer = speechsdk.SpeechRecognizer(speech_config=self.speech_config, audio_config=audio_config)
+        result = speech_recognizer.recognize_once()
+        if result.reason == speechsdk.ResultReason.RecognizedSpeech:
+            logger.info('[Azure] voiceToText voice file name={} text={}'.format(voice_file, result.text))
+            reply = Reply(ReplyType.TEXT, result.text)
+        else:
+            logger.error('[Azure] voiceToText error, result={}'.format(result))
+            reply = Reply(ReplyType.ERROR, "抱歉，语音识别失败")
+        return reply
+
+    def textToVoice(self, text):
+        fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
+        audio_config = speechsdk.AudioConfig(filename=fileName)
+        speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=self.speech_config, audio_config=audio_config)
+        result = speech_synthesizer.speak_text(text)
+        if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
+            logger.info(
+                '[Azure] textToVoice text={} voice file name={}'.format(text, fileName))
+            reply = Reply(ReplyType.VOICE, fileName)
+        else:
+            logger.error('[Azure] textToVoice error, result={}'.format(result))
+            reply = Reply(ReplyType.ERROR, "抱歉，语音合成失败")
+        return reply
diff --git a/voice/azure/config.json.template b/voice/azure/config.json.template
new file mode 100644
index 0000000..13b1fbd
--- /dev/null
+++ b/voice/azure/config.json.template
@@ -0,0 +1,4 @@
+{
+    "speech_synthesis_voice_name": "zh-CN-XiaoxiaoNeural",
+    "speech_recognition_language": "zh-CN"
+}
\ No newline at end of file
diff --git a/voice/voice_factory.py b/voice/voice_factory.py
index 591e346..de4b3d9 100644
--- a/voice/voice_factory.py
+++ b/voice/voice_factory.py
@@ -20,4 +20,7 @@ def create_voice(voice_type):
     elif voice_type == 'pytts':
         from voice.pytts.pytts_voice import PyttsVoice
         return PyttsVoice()
+    elif voice_type == 'azure':
+        from voice.azure.azure_voice import AzureVoice
+        return AzureVoice()
     raise RuntimeError