Merge pull request #1135 from AstrBotDevs/feat-dashscope-tts

✨feat: 支持阿里云百炼 TTS

astrbot/core/config/default.py

@@ -671,8 +671,22 @@ CONFIG_METADATA_2 = {
                         "fishaudio-tts-character": "可莉",
                         "timeout": "20",
                     },
+                    "阿里云百炼_TTS(API)": {
+                        "id": "dashscope_tts",
+                        "type": "dashscope_tts",
+                        "enable": False,
+                        "api_key": "",
+                        "model": "cosyvoice-v1",
+                        "dashscope_tts_voice": "loongstella",
+                        "timeout": "20",
+                    },
                 },
                 "items": {
+                    "dashscope_tts_voice": {
+                        "description": "语音合成模型",
+                        "type": "string",
+                        "hint": "阿里云百炼语音合成模型名称。具体可参考 https://help.aliyun.com/zh/model-studio/developer-reference/cosyvoice-python-api 等内容",
+                    },
                     "gm_resp_image_modal": {
                         "description": "启用图片模态",
                         "type": "bool",

astrbot/core/provider/manager.py

@@ -198,6 +198,10 @@ class ProviderManager:
                     from .sources.fishaudio_tts_api_source import (
                         ProviderFishAudioTTSAPI as ProviderFishAudioTTSAPI,
                     )
+                case "dashscope_tts":
+                    from .sources.dashscope_tts import (
+                        ProviderDashscopeTTSAPI as ProviderDashscopeTTSAPI,
+                    )
         except (ImportError, ModuleNotFoundError) as e:
             logger.critical(
                 f"加载 {provider_config['type']}({provider_config['id']}) 提供商适配器失败：{e}。可能是因为有未安装的依赖。"

astrbot/core/provider/sources/dashscope_tts.py

@@ -0,0 +1,39 @@
+import dashscope
+import uuid
+import asyncio
+from dashscope.audio.tts_v2 import *
+from ..provider import TTSProvider
+from ..entites import ProviderType
+from ..register import register_provider_adapter
+
+
+@register_provider_adapter(
+    "dashscope_tts", "Dashscope TTS API", provider_type=ProviderType.TEXT_TO_SPEECH
+)
+class ProviderDashscopeTTSAPI(TTSProvider):
+    def __init__(
+        self,
+        provider_config: dict,
+        provider_settings: dict,
+    ) -> None:
+        super().__init__(provider_config, provider_settings)
+        self.chosen_api_key: str = provider_config.get("api_key", "")
+        self.voice: str = provider_config.get("dashscope_tts_voice", "loongstella")
+        self.set_model(provider_config.get("model", None))
+        self.timeout_ms = float(provider_config.get("timeout", 20))*1000
+
+        dashscope.api_key = self.chosen_api_key
+        self.synthesizer = SpeechSynthesizer(
+            model=self.get_model(),
+            voice=self.voice,
+            format=AudioFormat.WAV_24000HZ_MONO_16BIT,
+        )
+
+    async def get_audio(self, text: str) -> str:
+        path = f"data/temp/dashscope_tts_{uuid.uuid4()}.wav"
+        audio = await asyncio.get_event_loop().run_in_executor(
+            None, self.synthesizer.call, text, self.timeout_ms
+        )
+        with open(path, "wb") as f:
+            f.write(audio)
+        return path