add ElevenLabs TTS to voice factory

config.py

@@ -61,7 +61,7 @@
     "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
     "always_reply_voice": False,  # 是否一直使用语音回复
     "voice_to_text": "openai",  # 语音识别引擎，支持openai,baidu,google,azure
-    "text_to_voice": "baidu",  # 语音合成引擎，支持baidu,google,pytts(offline),azure
+    "text_to_voice": "baidu",  # 语音合成引擎，支持baidu,google,pytts(offline),azure,elevenlabs
     # 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": "",
@@ -71,6 +71,9 @@
     # 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",
+    # elevenlabs 语音api配置
+    "xi_api_key": "",    #获取ap的方法可以参考https://docs.elevenlabs.io/api-reference/quick-start/authentication
+    "xi_voice_id": "",   #ElevenLabs提供了9种英式、美式等英语发音id，分别是“Adam/Antoni/Arnold/Bella/Domi/Elli/Josh/Rachel/Sam”
     # 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

voice/elevent/elevent_voice.py

@@ -0,0 +1,79 @@
+"""
+eleventLabs voice service
+
+["voice_id":"pNInz6obpgDQGcFmaJgB","name":"Adam"]
+["voice_id":"ErXwobaYiN019PkySvjV","name":"Antoni"]
+["voice_id":"VR6AewLTigWG4xSOukaG","name":"Arnold"]
+["voice_id":"EXAVITQu4vr4xnSDxMaL","name":"Bella"]
+["voice_id":"AZnzlk1XvdvUeBnXmlld","name":"Domi"]
+["voice_id":"MF3mGyEYCl7XYWbV9V6O","name":"Elli"]
+["voice_id":"TxGEqnHWrfWFTfGW9XjX","name":"Josh"]
+["voice_id":"21m00Tcm4TlvDq8ikWAM","name":"Rachel"]
+["voice_id":"yoZ06aMxZJJ28mfd3POQ","name":"Sam"]
+
+"""
+
+import time
+import requests
+
+from elevenlabs import generate
+
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from common.tmp_dir import TmpDir
+from voice.voice import Voice
+from config import conf
+
+XI_API_KEY = conf().get("xi_api_key")
+name = conf().get("xi_voice_id")
+
+if name == "Adam":
+    voice_id = "pNInz6obpgDQGcFmaJgB"
+elif name == "Antoni":
+    voice_id = "ErXwobaYiN019PkySvjV"
+elif name == "Arnold":
+    voice_id = "VR6AewLTigWG4xSOukaG"
+elif name == "Bella":
+    voice_id = "EXAVITQu4vr4xnSDxMaL"
+elif name == "Domi":
+    voice_id = "AZnzlk1XvdvUeBnXmlld"
+elif name == "Elli":
+    voice_id = "MF3mGyEYCl7XYWbV9V6O"
+elif name == "Josh":
+    voice_id = "TxGEqnHWrfWFTfGW9XjX"
+elif name == "Rachel":
+    voice_id = "21m00Tcm4TlvDq8ikWAM"
+elif name == "Sam":
+    voice_id = "yoZ06aMxZJJ28mfd3POQ"
+
+
+class ElevenLabsVoice(Voice):
+
+    def __init__(self):
+        pass
+
+    def voiceToText(self, voice_file):
+        pass
+
+    def textToVoice(self, text):
+        url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}"
+        headers = {
+            "Accept": "audio/mpeg",
+            "Content-Type": "application/json",
+            "xi-api-key": XI_API_KEY
+        }
+        data = {
+            "text": text,
+            "model_id": "eleven_monolingual_v1",
+            "voice_settings": {
+                "stability": 0,
+                "similarity_boost": 0
+            }
+        }
+        response = requests.post(url, json=data, headers=headers)
+        audio = response.content
+        fileName = TmpDir().path() + "reply-" + str(int(time.time())) + "-" + str(hash(text) & 0x7FFFFFFF) + ".mp3"
+        with open(fileName, "wb") as f:
+            f.write(audio)
+        logger.info("[ElevenLabs] textToVoice text={} voice file name={}".format(text, fileName))
+        return Reply(ReplyType.VOICE, fileName)

voice/factory.py

@@ -29,4 +29,8 @@ def create_voice(voice_type):
         from voice.azure.azure_voice import AzureVoice
 
         return AzureVoice()
+    elif voice_type == "elevenlabs":
+        from voice.elevent.elevent_voice import ElevenLabsVoice
+
+        return ElevenLabsVoice()
     raise RuntimeError