feat: add tts speech model

bridge/bridge.py

@@ -31,7 +31,7 @@ class Bridge(object):
             self.btype["chat"] = const.LINKAI
             if not conf().get("voice_to_text") or conf().get("voice_to_text") in ["openai"]:
                 self.btype["voice_to_text"] = const.LINKAI
-            if not conf().get("text_to_voice") or conf().get("text_to_voice") in [const.TTS_1, const.TTS_1_HD]:
+            if not conf().get("text_to_voice") or conf().get("text_to_voice") in ["openai", const.TTS_1, const.TTS_1_HD]:
                 self.btype["text_to_voice"] = const.LINKAI
         if model_type in ["claude"]:
             self.btype["chat"] = const.CLAUDEAI

config.py

@@ -73,7 +73,8 @@ available_setting = {
     "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": "tts-1",  # 语音合成引擎，支持tts-1,tts-1-hd,baidu,google,pytts(offline),azure,elevenlabs
+    "text_to_voice": "openai",  # 语音合成引擎，支持openai,baidu,google,pytts(offline),azure,elevenlabs
+    "text_to_voice_model": "tts-1",
     "tts_voice_id": "alloy",
     # 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": "",

voice/linkai/linkai_voice.py

@@ -53,8 +53,8 @@ class LinkAIVoice(Voice):
             url = conf().get("linkai_api_base", "https://api.link-ai.chat") + "/v1/audio/speech"
             headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
             model = const.TTS_1
-            if not conf().get("text_to_voice") or conf().get("text_to_voice") in [const.TTS_1, const.TTS_1_HD]:
+            if not conf().get("text_to_voice") or conf().get("text_to_voice") in ["openai", const.TTS_1, const.TTS_1_HD]:
-                model = conf().get("text_to_voice") or const.TTS_1
+                model = conf().get("text_to_voice_model") or const.TTS_1
             data = {
                 "model": model,
                 "input": text,

voice/openai/openai_voice.py

@@ -9,7 +9,9 @@ from bridge.reply import Reply, ReplyType
 from common.log import logger
 from config import conf
 from voice.voice import Voice
-
+import requests
+from common import const
+import datetime, random
 
 class OpenaiVoice(Voice):
     def __init__(self):
@@ -27,3 +29,28 @@ class OpenaiVoice(Voice):
             reply = Reply(ReplyType.ERROR, "我暂时还无法听清您的语音，请稍后再试吧~")
         finally:
             return reply
+
+
+    def textToVoice(self, text):
+        try:
+            url = 'https://api.openai.com/v1/audio/speech'
+            headers = {
+                'Authorization': 'Bearer ' + conf().get("open_ai_api_key"),
+                'Content-Type': 'application/json'
+            }
+            data = {
+                'model': conf().get("text_to_voice_model") or const.TTS_1,
+                'input': text,
+                'voice': conf().get("tts_voice_id") or "alloy"
+            }
+            response = requests.post(url, headers=headers, json=data)
+            file_name = "tmp/" + datetime.datetime.now().strftime('%Y%m%d%H%M%S') + str(random.randint(0, 1000)) + ".mp3"
+            logger.debug(f"[OPENAI] text_to_Voice file_name={file_name}, input={text}")
+            with open(file_name, 'wb') as f:
+                f.write(response.content)
+            logger.info(f"[OPENAI] text_to_Voice success")
+            reply = Reply(ReplyType.VOICE, file_name)
+        except Exception as e:
+            logger.error(e)
+            reply = Reply(ReplyType.ERROR, "遇到了一点小问题，请稍后再问我吧")
+        return reply