minimax语音tts和阿里云智能语音tts适配

config.yaml

@@ -217,3 +217,58 @@ TTS:
     parallel_infer: true
     repetition_penalty: 1.35
     aux_ref_audio_paths: []
+  MinimaxTTS:
+    # Minimax语音合成服务，需要先在minimax平台创建账户充值，并获取登录信息
+    # 平台地址：https://platform.minimaxi.com/
+    # 充值地址：https://platform.minimaxi.com/user-center/payment/balance
+    # group_id地址：https://platform.minimaxi.com/user-center/basic-information
+    # api_key地址：https://platform.minimaxi.com/user-center/basic-information/interface-key
+    # 定义TTS API类型
+    type: minimax
+    output_file: tmp/
+    group_id: 你的minimax平台groupID
+    api_key: 你的minimax平台接口密钥
+    model: "speech-01-turbo"
+    # 此处设置将优先于voice_setting中voice_id的设置；如都不设置，默认为 female-shaonv
+    voice_id: "female-shaonv"
+    # 以下可不用设置，使用默认设置
+    # voice_setting:
+    #     voice_id: "male-qn-qingse"
+    #     speed: 1
+    #     vol: 1
+    #     pitch: 0
+    #     emotion: "happy"
+    # pronunciation_dict:
+    #     tone:
+    #       - "处理/(chu3)(li3)"
+    #       - "危险/dangerous"
+    # audio_setting:
+    #     sample_rate: 32000
+    #     bitrate: 128000
+    #     format: "mp3"
+    #     channel: 1
+    # timber_weights:
+    #   -
+    #     voice_id: male-qn-qingse
+    #     weight: 1
+    #   -
+    #     voice_id: female-shaonv
+    #     weight: 1
+    # language_boost: auto
+  AliyunTTS:
+    # 阿里云智能语音交互服务，需要先在阿里云平台开通服务，然后获取验证信息
+    # 平台地址：https://nls-portal.console.aliyun.com/
+    # appkey地址：https://nls-portal.console.aliyun.com/applist
+    # token地址：https://nls-portal.console.aliyun.com/overview
+    # 定义TTS API类型
+    type: aliyun
+    output_file: tmp/
+    appkey: 你的阿里云智能语音交互服务项目Appkey
+    token: 你的阿里云智能语音交互服务AccessToken
+    voice: xiaoyun
+    # 以下可不用设置，使用默认设置
+    # format: wav
+    # sample_rate: 16000
+    # volume: 50
+    # speech_rate: 0
+    # pitch_rate: 0

core/providers/tts/aliyun.py

@@ -0,0 +1,57 @@
+import os
+import uuid
+import json
+import requests
+from datetime import datetime
+from core.providers.tts.base import TTSProviderBase
+
+import http.client
+import urllib.parse
+
+
+class TTSProvider(TTSProviderBase):
+    def __init__(self, config, delete_audio_file):
+        super().__init__(config, delete_audio_file)
+        self.appkey = config.get("appkey")
+        self.token = config.get("token")
+        self.format = config.get("format", "wav")
+        self.sample_rate = config.get("sample_rate", 16000)
+        self.voice = config.get("voice", "xiaoyun")
+        self.volume = config.get("volume", 50)
+        self.speech_rate = config.get("speech_rate", 0)
+        self.pitch_rate = config.get("pitch_rate", 0)
+
+        self.host = config.get("host", "nls-gateway-cn-shanghai.aliyuncs.com")
+        self.api_url = f"https://{self.host}/stream/v1/tts"
+        self.header = {
+            "Content-Type": "application/json"
+        }
+
+    def generate_filename(self, extension=".wav"):
+        return os.path.join(self.output_file, f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+
+    async def text_to_speak(self, text, output_file):
+        request_json = {
+            "appkey": self.appkey,
+            "token": self.token,
+            "text": text,
+            "format": self.format,
+            "sample_rate": self.sample_rate,
+            "voice": self.voice,
+            "volume": self.volume,
+            "speech_rate": self.speech_rate,
+            "pitch_rate": self.pitch_rate
+        }
+
+        print(self.api_url, json.dumps(request_json, ensure_ascii=False))
+        try:
+            resp = requests.post(self.api_url, json.dumps(request_json), headers=self.header)
+            # 检查返回请求数据的mime类型是否是audio/***，是则保存到指定路径下；返回的是binary格式的
+            if resp.headers['Content-Type'].startswith('audio/'):
+                with open(output_file, 'wb') as f:
+                    f.write(resp.content)
+                return output_file
+            else:
+                raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
+        except Exception as e:
+            raise Exception(f"{__name__} error: {e}")

core/providers/tts/minimax.py

@@ -0,0 +1,77 @@
+import os
+import uuid
+import json
+import requests
+from datetime import datetime
+from core.providers.tts.base import TTSProviderBase
+
+
+class TTSProvider(TTSProviderBase):
+    def __init__(self, config, delete_audio_file):
+        super().__init__(config, delete_audio_file)
+        self.group_id = config.get("group_id")
+        self.api_key = config.get("api_key")
+        self.model = config.get("model")
+        self.voice_id = config.get("voice_id")
+
+        default_voice_setting = {
+            "voice_id": "female-shaonv",
+            "speed": 1,
+            "vol": 1,
+            "pitch": 0,
+            "emotion": "happy"
+        }
+        default_pronunciation_dict = {
+            "tone": [
+                "处理/(chu3)(li3)", "危险/dangerous"
+            ]
+        }
+        defult_audio_setting = {
+            "sample_rate": 32000,
+            "bitrate": 128000,
+            "format": "mp3",
+            "channel": 1
+        }
+        self.voice_setting = {**default_voice_setting, **config.get("voice_setting", {})}
+        self.pronunciation_dict = {**default_pronunciation_dict, **config.get("pronunciation_dict", {})}
+        self.audio_setting = {**defult_audio_setting, **config.get("audio_setting", {})}
+        self.timber_weights = config.get("timber_weights", [])
+
+        if self.voice_id:
+            self.voice_setting["voice_id"] = self.voice_id
+
+        self.host = "api.minimax.chat"
+        self.api_url = f"https://{self.host}/v1/t2a_v2?GroupId={self.group_id}"
+        self.header = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {self.api_key}"
+        }
+
+    def generate_filename(self, extension=".mp3"):
+        return os.path.join(self.output_file, f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+
+    async def text_to_speak(self, text, output_file):
+        request_json = {
+            "model": self.model,
+            "text": text,
+            "stream": False,
+            "voice_setting": self.voice_setting,
+            "pronunciation_dict": self.pronunciation_dict,
+            "audio_setting": self.audio_setting,
+        }
+
+        if type(self.timber_weights) is list and len(self.timber_weights) > 0:
+            request_json["timber_weights"] = self.timber_weights
+            request_json["voice_setting"]["voice_id"] = ""
+
+        try:
+            resp = requests.post(self.api_url, json.dumps(request_json), headers=self.header)
+            # 检查返回请求数据的status_code是否为0
+            if resp.json()["base_resp"]["status_code"] == 0:
+                data = resp.json()['data']['audio']
+                file_to_save = open(output_file, "wb")
+                file_to_save.write(bytes.fromhex(data))
+            else:
+                raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
+        except Exception as e:
+            raise Exception(f"{__name__} error: {e}")