chore: v3.4.13

适配 OpenAI TTS API，并支持 Napcat，Gewechat，Lagrange 的语音输出

README.md

@@ -1,14 +1,12 @@
-
 <p align="center">
+    
+![](https://github.com/user-attachments/assets/04f22f63-4dcf-4a6c-981e-b33f45c23f3e)
 
-<img src="https://github.com/user-attachments/assets/de10f24d-cd64-433a-90b8-16c0a60de24a" width=500>
 
 </p>
 
 <div align="center">
 
-<h1>AstrBot</h1>
-
 _✨ 易上手的多平台 LLM 聊天机器人及开发框架 ✨_
 
 [![GitHub release (latest by date)](https://img.shields.io/github/v/release/Soulter/AstrBot)](https://github.com/Soulter/AstrBot/releases/latest)
@@ -72,7 +70,7 @@ AstrBot 是一个松耦合、异步、支持多消息平台部署、具有易用
 | -------- | ------- | ------- | ------ |
 | QQ      | ✔    | 私聊、群聊 | 文字、图片、语音 |
 | QQ 官方API | ✔    | 私聊、群聊，QQ 频道私聊、群聊 | 文字、图片 |
-| 微信    | ✔    | [Gewechat](https://github.com/Devo919/Gewechat)。微信个人号私聊、群聊 | 文字 |
+| 微信    | ✔    | [Gewechat](https://github.com/Devo919/Gewechat)。微信个人号私聊、群聊 | 文字、图片、语音 |
 | [Telegram](https://github.com/Soulter/astrbot_plugin_telegram)   | ✔    | 私聊、群聊 | 文字、图片 |
 | 微信对话开放平台 | 🚧    | 计划内 | - |
 | 飞书   | 🚧    | 计划内 | - |
@@ -126,6 +124,13 @@ _✨ 内置 Web Chat，在线与机器人交互 ✨_
 
 </div>
 
+## ⭐ Star History
+
+> [!TIP] 
+> 如果本项目对您的生活 / 工作产生了帮助，或者您关注本项目的未来发展，请给项目 Star，这是我维护这个开源项目的动力 <3
+
+[![Star History Chart](https://api.star-history.com/svg?repos=soulter/astrbot&type=Date)](https://star-history.com/#soulter/astrbot&Date)
+
 
 <!-- ## ✨ ATRI [Beta 测试]
 

astrbot/core/config/default.py

@@ -2,7 +2,7 @@
 如需修改配置，请在 `data/cmd_config.json` 中修改或者在管理面板中可视化修改。
 """
 
-VERSION = "3.4.10"
+VERSION = "3.4.13"
 DB_PATH = "data/data_v3.db"
 
 # 默认配置
@@ -24,6 +24,13 @@ DEFAULT_CONFIG = {
         "wl_ignore_admin_on_friend": True,
         "reply_with_mention": False,
         "reply_with_quote": False,
+        "path_mapping": [],
+        "segmented_reply": {
+            "enable": False,
+            "only_llm_result": True,
+            "interval": "1.5,3.5",
+            "regex": ".*?[。？！~…]+|.+$"
+        }
     },
     "provider": [],
     "provider_settings": {
@@ -39,6 +46,10 @@ DEFAULT_CONFIG = {
         "enable": False,
         "provider_id": "",
     },
+    "provider_tts_settings": {
+        "enable": False,
+        "provider_id": "",
+    },
     "content_safety": {
         "internal_keywords": {"enable": True, "extra_keywords": []},
         "baidu_aip": {"enable": False, "app_id": "", "api_key": "", "secret_key": ""},
@@ -177,6 +188,31 @@ CONFIG_METADATA_2 = {
                             },
                         },
                     },
+                    "segmented_reply": {
+                        "description": "分段回复",
+                        "type": "object",
+                        "items": {
+                            "enable": {
+                                "description": "启用分段回复",
+                                "type": "bool",
+                            },
+                            "only_llm_result": {
+                                "description": "仅对 LLM 结果分段",
+                                "type": "bool",
+                            },
+                            "interval": {
+                                "description": "随机间隔时间(秒)",
+                                "type": "string",
+                                "hint": "每一段回复的间隔时间，格式为 `最小时间,最大时间`。如 `0.75,2.5`",
+                            },
+                            "regex": {
+                                "description": "正则表达式",
+                                "type": "string",
+                                "obvious_hint": True,
+                                "hint": "用于分隔一段消息。默认情况下会根据句号、问号等标点符号分隔。re.findall(r'<regex>', text)",
+                            },
+                        },
+                    },
                     "reply_prefix": {
                         "description": "回复前缀",
                         "type": "string",
@@ -220,6 +256,12 @@ CONFIG_METADATA_2 = {
                         "type": "bool",
                         "hint": "启用后，机器人回复消息时会引用原消息。实际效果以具体的平台适配器为准。",
                     },
+                    "path_mapping": {
+                        "description": "路径映射",
+                        "type": "list",
+                        "obvious_hint": True,
+                        "hint": "此功能解决由于文件系统不一致导致路径不存在的问题。格式为 <原路径>:<映射路径>。如 `/app/.config/QQ:/var/lib/docker/volumes/xxxx/_data`。这样，当消息平台下发的事件中图片和语音路径以 `/app/.config/QQ` 开头时，开头被替换为 `/var/lib/docker/volumes/xxxx/_data`。这在 AstrBot 或者平台协议端使用 Docker 部署时特别有用。",
+                    }
                 },
             },
             "content_safety": {
@@ -364,6 +406,14 @@ CONFIG_METADATA_2 = {
                         "type": "openai_whisper_selfhost",
                         "model": "tiny",
                     },
+                    "openai_tts(API)": {
+                        "id": "openai_tts",
+                        "type": "openai_tts_api",
+                        "enable": False,
+                        "api_key": "",
+                        "api_base": "",
+                        "model": "tts-1",
+                    },
                 },
                 "items": {
                     "whisper_hint": {
@@ -563,6 +613,23 @@ CONFIG_METADATA_2 = {
                     },
                 },
             },
+            "provider_tts_settings": {
+                "description": "文本转语音(TTS)",
+                "type": "object",
+                "items": {
+                    "enable": {
+                        "description": "启用文本转语音(TTS)",
+                        "type": "bool",
+                        "hint": "启用前请在 服务提供商配置 处创建支持 语音转文本任务 的提供商。如 openai_tts。",
+                        "obvious_hint": True,
+                    },
+                    "provider_id": {
+                        "description": "提供商 ID，不填则默认第一个TTS提供商",
+                        "type": "string",
+                        "hint": "文本转语音提供商 ID。如果不填写将使用载入的第一个提供商。",
+                    },
+                },
+            },
         },
     },
     "misc_config_group": {

astrbot/core/core_lifecycle.py

@@ -1,3 +1,4 @@
+import traceback
 import asyncio
 import time
 import threading
@@ -6,7 +7,6 @@ from .event_bus import EventBus
 from . import astrbot_config
 from asyncio import Queue
 from typing import List
-from astrbot.core.config.astrbot_config import AstrBotConfig
 from astrbot.core.pipeline.scheduler import PipelineScheduler, PipelineContext
 from astrbot.core.star import PluginManager
 from astrbot.core.platform.manager import PlatformManager
@@ -81,12 +81,30 @@ class AstrBotCoreLifecycle:
         for task in self.star_context._register_tasks:
             extra_tasks.append(asyncio.create_task(task, name=task.__name__))
         
-        self.curr_tasks = [event_bus_task, *platform_tasks, *extra_tasks]
+        # self.curr_tasks = [event_bus_task, *platform_tasks, *extra_tasks]
+        
+        tasks_ = [event_bus_task, *platform_tasks, *extra_tasks]
+        for task in tasks_:
+            self.curr_tasks.append(asyncio.create_task(self._task_wrapper(task), name=task.get_name()))
+        
         self.start_time = int(time.time())
+        
+    async def _task_wrapper(self, task: asyncio.Task):
+        try:
+            await task
+        except asyncio.CancelledError:
+            pass
+        except Exception as e:
+            
+            logger.error(f"------- 任务 {task.get_name()} 发生错误: {e}")
+            for line in traceback.format_exc().split("\n"):
+                logger.error(f"|    {line}")
+            logger.error("-------")
     
     async def start(self):
         self._load()
         logger.info("AstrBot 启动完成。")
+        
         await asyncio.gather(*self.curr_tasks, return_exceptions=True)
         
     async def stop(self):

astrbot/core/message/components.py

@@ -123,7 +123,7 @@ class Record(BaseMessageComponent):
     proxy: T.Optional[bool] = True
     timeout: T.Optional[int] = 0
     # 额外
-    path: T.Optional[str] # 用这个
+    path: T.Optional[str]
 
     def __init__(self, file: T.Optional[str], **_):
         for k in _.keys():

astrbot/core/message/message_event_result.py

@@ -13,12 +13,10 @@ class MessageChain():
     Attributes:
         `chain` (list): 用于顺序存储各个组件。
         `use_t2i_` (bool): 用于标记是否使用文本转图片服务。默认为 None，即跟随用户的设置。当设置为 True 时，将会使用文本转图片服务。
-        `is_split_` (bool): 用于标记是否分条发送消息。默认为 False。启用后，将会依次发送 chain 中的每个 component。
     '''
     
     chain: List[BaseMessageComponent] = field(default_factory=list)
     use_t2i_: Optional[bool] = None # None 为跟随用户设置
-    is_split_: Optional[bool] = False # 是否将消息分条发送。默认为 False。启用后，将会依次发送 chain 中的每个 component。
     
     def message(self, message: str):
         '''添加一条文本消息到消息链 `chain` 中。
@@ -77,16 +75,6 @@ class MessageChain():
         '''
         self.use_t2i_ = use_t2i
         return self
-    
-    def is_split(self, is_split: bool):
-        '''设置是否分条发送消息。默认为 False。启用后，将会依次发送 chain 中的每个 component。
-        
-        Note:
-            具体的效果以各适配器实现为准。
-            
-        '''
-        self.is_split_ = is_split
-        return self
 
 class EventResultType(enum.Enum):
     '''用于描述事件处理的结果类型。
@@ -113,7 +101,6 @@ class MessageEventResult(MessageChain):
     Attributes:
         `chain` (list): 用于顺序存储各个组件。
         `use_t2i_` (bool): 用于标记是否使用文本转图片服务。默认为 None，即跟随用户的设置。当设置为 True 时，将会使用文本转图片服务。
-        `is_split_` (bool): 用于标记是否分条发送消息。默认为 False。启用后，将会依次发送 chain 中的每个 component。
         `result_type` (EventResultType): 事件处理的结果类型。
     '''
     
@@ -139,7 +126,7 @@ class MessageEventResult(MessageChain):
         '''
         return self.result_type == EventResultType.STOP
     
-    def set_result_content_type(self, typ: EventResultType) -> 'MessageEventResult':
+    def set_result_content_type(self, typ: ResultContentType) -> 'MessageEventResult':
         '''设置事件处理的结果类型。
         
         Args:
@@ -148,5 +135,10 @@ class MessageEventResult(MessageChain):
         self.result_content_type = typ
         return self
     
+    def is_llm_result(self) -> bool:
+        '''是否为 LLM 结果。
+        '''
+        return self.result_content_type == ResultContentType.LLM_RESULT
+    
     
 CommandResult = MessageEventResult

astrbot/core/pipeline/preprocess_stage/stage.py

@@ -5,7 +5,7 @@ from ..stage import Stage, register_stage
 from ..context import PipelineContext
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from astrbot.core import logger
-from astrbot.core.message.components import Plain, Record
+from astrbot.core.message.components import Plain, Record, Image
 
 @register_stage
 class PreProcessStage(Stage):
@@ -16,26 +16,39 @@ class PreProcessStage(Stage):
         self.plugin_manager = ctx.plugin_manager
         
         self.stt_settings: dict = self.config.get('provider_stt_settings', {})
+        self.platform_settings: dict = self.config.get('platform_settings', {})
         
 
     async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
         '''在处理事件之前的预处理'''
-
+        # 路径映射
+        if mappings := self.platform_settings.get('path_mapping', []):
+            # 支持 Record，Image 消息段的路径映射。
+            message_chain = event.get_messages()
+            
+            for idx, component in enumerate(message_chain):
+                if isinstance(component, (Record, Image)) and component.url:
+                    for mapping in mappings:
+                        from_, to_ = mapping.split(":")
+                        from_ = from_.removesuffix("/")
+                        to_ = to_.removesuffix("/")
+                        
+                        url = component.url.removeprefix("file://")
+                        if url.startswith(from_):
+                            component.url = url.replace(from_, to_, 1)
+                            logger.debug(f"路径映射: {url} -> {component.url}")
+                    message_chain[idx] = component
+        
+        # STT
         if self.stt_settings.get('enable', False):
-            # STT 处理
             # TODO: 独立
             stt_provider = self.plugin_manager.context.provider_manager.curr_stt_provider_inst
             if stt_provider:
                 message_chain = event.get_messages()
                 for idx, component in enumerate(message_chain):
                     if isinstance(component, Record) and component.url:
-                        
-                        path = component.url
-                        
-                        path.removeprefix("file:///")
-                        
+                        path = component.url.removeprefix("file://")
                         retry = 5
-                        
                         for i in range(retry):
                             try:
                                 result = await stt_provider.get_text(audio_url=path)
@@ -48,7 +61,7 @@ class PreProcessStage(Stage):
                             except FileNotFoundError as e:
                                 # napcat workaround
                                 logger.warning(e)
-                                logger.warning(f"语音文件不存在: {path}, 重试中: {i + 1}/{retry}")
+                                logger.warning(f"重试中: {i + 1}/{retry}")
                                 await asyncio.sleep(0.5)
                                 continue
                             except BaseException as e:

astrbot/core/pipeline/process_stage/method/llm_request.py

@@ -51,7 +51,7 @@ class LLMRequestSubStage(Stage):
             session_provider_context = provider.session_memory.get(event.session_id)
             req.contexts = session_provider_context if session_provider_context else []
             
-        if not req.prompt:
+        if not req.prompt and not req.image_urls:
             return
             
         # 执行请求 LLM 前事件。

astrbot/core/pipeline/respond/stage.py

@@ -1,7 +1,10 @@
+import random
+import asyncio
 from typing import Union, AsyncGenerator
 from ..stage import register_stage, Stage
 from ..context import PipelineContext
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
+from astrbot.core.message.message_event_result import MessageChain
 from astrbot.core import logger
 from astrbot.core.star.star_handler import star_handlers_registry, EventType
 
@@ -9,6 +12,17 @@ from astrbot.core.star.star_handler import star_handlers_registry, EventType
 class RespondStage(Stage):
     async def initialize(self, ctx: PipelineContext):
         self.ctx = ctx
+        
+        # 分段回复
+        self.enable_seg: bool = ctx.astrbot_config['platform_settings']['segmented_reply']['enable']
+        interval_str: str = ctx.astrbot_config['platform_settings']['segmented_reply']['interval']
+        interval_str_ls = interval_str.replace(" ", "").split(",")
+        try:
+            self.interval = [float(t) for t in interval_str_ls]
+        except BaseException as e:
+            logger.error(f'解析分段回复的间隔时间失败。{e}')
+            self.interval = [1.5, 3.5]
+
 
     async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
         result = event.get_result()
@@ -16,7 +30,15 @@ class RespondStage(Stage):
             return
 
         if len(result.chain) > 0:
-            await event.send(result)
+            await event._pre_send()
+            if self.enable_seg:
+                # 分段回复
+                for comp in result.chain:
+                    await event.send(MessageChain([comp]))
+                await asyncio.sleep(random.uniform(self.interval[0], self.interval[1]))
+            else:
+                await event.send(result)
+            await event._post_send()
             logger.info(f"AstrBot -> {event.get_sender_name()}/{event.get_sender_id()}: {event._outline_chain(result.chain)}")
         
         handlers = star_handlers_registry.get_handlers_by_event_type(EventType.OnAfterMessageSentEvent)

astrbot/core/pipeline/result_decorate/stage.py

@@ -1,11 +1,13 @@
 import time
+import re
+import traceback
 from typing import Union, AsyncGenerator
 from ..stage import register_stage
 from ..context import PipelineContext
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from astrbot.core.platform.message_type import MessageType
 from astrbot.core import logger
-from astrbot.core.message.components import Plain, Image, At, Reply
+from astrbot.core.message.components import Plain, Image, At, Reply, Record
 from astrbot.core import html_renderer
 from astrbot.core.star.star_handler import star_handlers_registry, EventType
 
@@ -16,7 +18,13 @@ class ResultDecorateStage:
         self.reply_prefix = ctx.astrbot_config['platform_settings']['reply_prefix']
         self.reply_with_mention = ctx.astrbot_config['platform_settings']['reply_with_mention']
         self.reply_with_quote = ctx.astrbot_config['platform_settings']['reply_with_quote']
+        self.use_tts = ctx.astrbot_config['provider_tts_settings']['enable']
         self.t2i = ctx.astrbot_config['t2i']
+        
+        # 分段回复
+        self.enable_segmented_reply = ctx.astrbot_config['platform_settings']['segmented_reply']['enable']
+        self.only_llm_result = ctx.astrbot_config['platform_settings']['segmented_reply']['only_llm_result']
+        self.regex = ctx.astrbot_config['platform_settings']['segmented_reply']['regex']
 
     async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
         result = event.get_result()
@@ -31,10 +39,53 @@ class ResultDecorateStage:
         if len(result.chain) > 0:
             # 回复前缀
             if self.reply_prefix:
-                result.chain.insert(0, Plain(self.reply_prefix))
+                for comp in result.chain:
+                    if isinstance(comp, Plain):
+                        comp.text = self.reply_prefix + comp.text
+                        break
+            
+             # 分段回复 
+            if self.enable_segmented_reply:
+                if (self.only_llm_result and result.is_llm_result()) or not self.only_llm_result:
+                    new_chain = []
+                    for comp in result.chain:
+                        if isinstance(comp, Plain):
+                            split_response = re.findall(r".*?[。？！~…]+|.+$", comp.text)
+                            if not split_response:
+                                new_chain.append(comp)
+                                continue
+                            for seg in split_response:
+                                new_chain.append(Plain(seg))
+                        else:
+                            # 非 Plain 类型的消息段不分段
+                            new_chain.append(comp)
+                    result.chain = new_chain
+                
+            # TTS
+            if self.use_tts and result.is_llm_result():
+                tts_provider = self.ctx.plugin_manager.context.provider_manager.curr_tts_provider_inst
+                new_chain = []
+                for comp in result.chain:
+                    if isinstance(comp, Plain) and len(comp.text) > 1:
+                        try:
+                            logger.info("TTS 请求: " + plain_str)
+                            audio_path = await tts_provider.get_audio(plain_str)
+                            logger.info("TTS 结果: " + audio_path)
+                            if audio_path:
+                                new_chain.append(Record(file=audio_path, url=audio_path))
+                            else:
+                                logger.error(f"由于 TTS 音频文件没找到，消息段转语音失败: {comp.text}")
+                                new_chain.append(comp)
+                        except BaseException:
+                            traceback.print_exc()
+                            logger.error("TTS 失败，使用文本发送。")
+                            new_chain.append(comp)
+                    else:
+                        new_chain.append(comp)
+                result.chain = new_chain
             
             # 文本转图片
-            if (result.use_t2i_ is None and self.t2i) or result.use_t2i_:
+            elif (result.use_t2i_ is None and self.t2i) or result.use_t2i_:
                 plain_str = ""
                 for comp in result.chain:
                     if isinstance(comp, Plain):

astrbot/core/platform/astr_message_event.py

@@ -179,6 +179,15 @@ class AstrMessageEvent(abc.ABC):
         await Metric.upload(msg_event_tick = 1, adapter_name = self.platform_meta.name)
         self._has_send_oper = True
         
+    async def _pre_send(self):
+        '''调度器会在执行 send() 前调用该方法'''
+        pass
+    
+    async def _post_send(self):
+        '''调度器会在执行 send() 后调用该方法'''
+        pass
+        
+        
     def set_result(self, result: Union[MessageEventResult, str]):
         '''设置消息事件的结果。
         

astrbot/core/platform/register.py

@@ -27,6 +27,8 @@ def register_platform_adapter(
                 default_config_tmpl['type'] = adapter_name
             if 'enable' not in default_config_tmpl:
                 default_config_tmpl['enable'] = False
+            if 'id' not in default_config_tmpl:
+                default_config_tmpl['id'] = adapter_name
 
         pm = PlatformMetadata(
             name=adapter_name,

astrbot/core/platform/sources/aiocqhttp/aiocqhttp_message_event.py

@@ -3,7 +3,7 @@ import random
 import asyncio
 
 from astrbot.api.event import AstrMessageEvent, MessageChain
-from astrbot.api.message_components import Plain, Image
+from astrbot.api.message_components import Plain, Image, Record
 from aiocqhttp import CQHttp
 from astrbot.core.utils.io import file_to_base64, download_image_by_url
 
@@ -20,16 +20,18 @@ class AiocqhttpMessageEvent(AstrMessageEvent):
             d = segment.toDict()
             if isinstance(segment, Plain):
                 d['type'] = 'text'
-            if isinstance(segment, Image):
+            if isinstance(segment, (Image, Record)):
                 # convert to base64
                 if segment.file and segment.file.startswith("file:///"):
-                    image_base64 = file_to_base64(segment.file[8:])
+                    bs64_data = file_to_base64(segment.file[8:])
                     image_file_path = segment.file[8:]
                 elif segment.file and segment.file.startswith("http"):
                     image_file_path = await download_image_by_url(segment.file)
-                    image_base64 = file_to_base64(image_file_path)
+                    bs64_data = file_to_base64(image_file_path)
+                else:
+                    bs64_data = file_to_base64(segment.file)
                 d['data'] = {
-                    'file': image_base64,
+                    'file': bs64_data,
                 }
             ret.append(d)
         return ret
@@ -38,11 +40,5 @@ class AiocqhttpMessageEvent(AstrMessageEvent):
         ret = await AiocqhttpMessageEvent._parse_onebot_json(message)
         if os.environ.get('TEST_MODE', 'off') == 'on':
             return
-        
-        if message.is_split_: # 分条发送
-            for m in ret:
-                await self.bot.send(self.message_obj.raw_message, [m])
-                await asyncio.sleep(random.uniform(0.75, 2.5))
-        else:
-            await self.bot.send(self.message_obj.raw_message, ret)
+        await self.bot.send(self.message_obj.raw_message, ret)
         await super().send(message)

astrbot/core/platform/sources/gewechat/client.py

@@ -2,10 +2,14 @@ import threading
 import asyncio
 import aiohttp
 import quart
+import base64
 
 from astrbot.api.platform import AstrBotMessage, MessageMember, MessageType
-from astrbot.api.message_components import Plain, Image, At
+from astrbot.api.message_components import Plain, Image, At, Record
 from astrbot.api import logger, sp
+from .downloader import GeweDownloader
+from astrbot.core.utils.io import download_image_by_url
+
 
 class SimpleGewechatClient():
     '''针对 Gewechat 的简单实现。
@@ -17,9 +21,15 @@ class SimpleGewechatClient():
         self.base_url = base_url
         if self.base_url.endswith('/'):
             self.base_url = self.base_url[:-1]
+            
+        self.download_base_url = self.base_url.split(':')[:-1] # 去掉端口
+        self.download_base_url = ':'.join(self.download_base_url) + ":2532/download/"
         
         self.base_url += "/v2/api"
         
+        logger.info(f"Gewechat API: {self.base_url}")
+        logger.info(f"Gewechat 下载 API: {self.download_base_url}")
+        
         if isinstance(port, str):
             port = int(port)
             
@@ -27,15 +37,19 @@ class SimpleGewechatClient():
         self.headers = {}
         self.nickname = nickname
         self.appid = sp.get(f"gewechat-appid-{nickname}", "")
-        self.callback_url = None
         
         self.server = quart.Quart(__name__)
-        self.server.add_url_rule('/astrbot-gewechat/callback', view_func=self.callback, methods=['POST'])  
+        self.server.add_url_rule('/astrbot-gewechat/callback', view_func=self.callback, methods=['POST'])
+        self.server.add_url_rule('/astrbot-gewechat/file/<file_id>', view_func=self.handle_file, methods=['GET'])
         
         self.host = host
         self.port = port 
+        self.callback_url = f"http://{self.host}:{self.port}/astrbot-gewechat/callback"
+        self.file_server_url = f"http://{self.host}:{self.port}/astrbot-gewechat/file"
         
         self.event_queue = event_queue
+        
+        self.multimedia_downloader = None
     
     async def get_token_id(self):
         async with aiohttp.ClientSession() as session:
@@ -54,54 +68,84 @@ class SimpleGewechatClient():
             return
         abm = AstrBotMessage()
         d = data['Data']
-        msg_type = d['MsgType']
+    
+        from_user_name = d['FromUserName']['string'] # 消息来源
+        d['to_wxid'] = from_user_name # 用于发信息
         
-        match msg_type:
+        abm.message_id = str(d.get('MsgId'))
+        abm.session_id = from_user_name
+        abm.self_id = data['Wxid'] # 机器人的 wxid
+        
+        user_id = "" # 发送人 wxid
+        content = d['Content']['string'] # 消息内容
+        
+        at_me = False
+        if "@chatroom" in from_user_name:
+            abm.type = MessageType.GROUP_MESSAGE
+            _t = content.split(':\n')
+            user_id = _t[0]
+            content = _t[1]
+            if '\u2005' in content: 
+                # at
+                content = content.split('\u2005')[1]
+            abm.group_id = from_user_name
+            # at
+            msg_source = d['MsgSource']
+            if f'<atuserlist><![CDATA[,{abm.self_id}]]>' in msg_source \
+                or f'<atuserlist><![CDATA[{abm.self_id}]]>' in msg_source:
+                at_me = True
+        else:
+            abm.type = MessageType.FRIEND_MESSAGE
+            user_id = from_user_name
+            
+        abm.message = []
+        if at_me:
+            abm.message.insert(0, At(qq=abm.self_id))
+        
+        user_real_name = d['PushContent'].split(' : ')[0] \
+            .replace('在群聊中@了你', '') \
+            .replace('在群聊中发了一段语音', '') # 真实昵称
+        abm.sender = MessageMember(user_id, user_real_name)
+        abm.raw_message = d
+        abm.message_str = ""
+        # 不同消息类型
+        match d['MsgType']:
             case 1:
-                from_user_name = d['FromUserName']['string'] # 消息来源
-                d['to_wxid'] = from_user_name # 用于发信息
-                
-                user_id = "" # 发送人 wxid
-                content = d['Content']['string'] # 消息内容
-                user_real_name = d['PushContent'].split(' : ')[0] # 真实昵称
-                user_real_name.replace('在群聊中@了你', '') # trick
-                abm.self_id = data['Wxid'] # 机器人的 wxid
-                at_me = False
-                if "@chatroom" in from_user_name:
-                    abm.type = MessageType.GROUP_MESSAGE
-                    _t = content.split(':\n')
-                    user_id = _t[0]
-                    content = _t[1]
-                    if '\u2005' in content: 
-                        # at
-                        content = content.split('\u2005')[1]
-                    
-                    abm.group_id = from_user_name
-                    
-                    # at
-                    msg_source = d['MsgSource']
-                    if f'<atuserlist><![CDATA[,{abm.self_id}]]>' in msg_source:
-                        at_me = True
-                    
-                else:
-                    abm.type = MessageType.FRIEND_MESSAGE
-                    user_id = from_user_name
-                abm.session_id = from_user_name
-                abm.sender = MessageMember(user_id, user_real_name)
-                abm.message = [Plain(content)]
-                
-                if at_me:
-                    abm.message.insert(0, At(qq=abm.self_id))
-                
-                abm.message_id = str(d['MsgId'])
-                abm.raw_message = d
+                # 文本消息
+                abm.message.append(Plain(content))
                 abm.message_str = content
+            case 3:
+                # 图片消息
+                file_url = await self.multimedia_downloader.download_image(
+                    self.appid, 
+                    content
+                )
+                logger.debug(f"下载图片: {file_url}")
+                file_path = await download_image_by_url(file_url)
+                abm.message.append(Image(file=file_path, url=file_path))
+                
+            case 34:
+                # 语音消息
+                # data = await self.multimedia_downloader.download_voice(
+                #     self.appid, 
+                #     content, 
+                #     abm.message_id
+                # )
+                # print(data)
+                if 'ImgBuf' in d and 'buffer' in d['ImgBuf']:
+                    voice_data = base64.b64decode(d['ImgBuf']['buffer'])
+                    file_path = f"data/temp/gewe_voice_{abm.message_id}.silk"
+                    with open(file_path, "wb") as f:
+                        f.write(voice_data)
+                    abm.message.append(Record(file=file_path, url=file_path))
                 
-                logger.info(f"abm: {abm}")
-                return abm
             case _:
-                logger.error(f"未实现的消息类型: {msg_type}")
-                
+                logger.error(f"未实现的消息类型: {d['MsgType']}")
+                return
+        
+        logger.info(f"abm: {abm}")
+        return abm
+
     async def callback(self):
         data = await quart.request.json
         logger.debug(f"收到 gewechat 回调: {data}")
@@ -117,32 +161,31 @@ class SimpleGewechatClient():
                 await coro(abm)
             
         return quart.jsonify({"r": "AstrBot ACK"})
+    
+    async def handle_file(self, file_id):
+        file_path = f"data/temp/{file_id}"
+        return await quart.send_file(file_path)
         
     async def _set_callback_url(self):
         logger.info("设置回调，请等待...")
         await asyncio.sleep(3)
-        callback_url = f"http://{self.host}:{self.port}/astrbot-gewechat/callback"
         async with aiohttp.ClientSession() as session:
             async with session.post(
                 f"{self.base_url}/tools/setCallback",
                 headers=self.headers,
                 json={
                     "token": self.token,
-                    "callbackUrl": callback_url
+                    "callbackUrl": self.callback_url
                 }
             ) as resp:
                 json_blob = await resp.json()
                 logger.info(f"设置回调结果: {json_blob}")
                 if json_blob['ret'] != 200:
                     raise Exception(f"设置回调失败: {json_blob}")
-                logger.info(f"将在 {callback_url} 上接收 gewechat 下发的消息。")
+                logger.info(f"将在 {self.callback_url} 上接收 gewechat 下发的消息。如果一直没收到消息请先尝试重启 AstrBot。")
         
     async def start_polling(self):
-        
-        # 设置回调
         threading.Thread(target=asyncio.run, args=(self._set_callback_url(),)).start()
-
-                
         await self.server.run_task(
             host=self.host, 
             port=self.port, 
@@ -185,6 +228,8 @@ class SimpleGewechatClient():
     async def login(self):
         if self.token is None:
             await self.get_token_id()
+            
+        self.multimedia_downloader = GeweDownloader(self.base_url, self.download_base_url, self.token)
         
         if self.appid:
             online = await self.check_online(self.appid)
@@ -243,7 +288,7 @@ class SimpleGewechatClient():
                         logger.warning(f"未知状态: {status}")
             await asyncio.sleep(5)
             
-        if not self.appid and appid:
+        if appid:
             sp.put(f"gewechat-appid-{nickname}", appid)
             self.appid = appid
             logger.info(f"已保存 APPID: {appid}")
@@ -262,4 +307,39 @@ class SimpleGewechatClient():
                 json=payload
             ) as resp:
                 json_blob = await resp.json()
-                logger.info(f"发送消息结果: {json_blob}")
+                logger.debug(f"发送消息结果: {json_blob}")
+                
+    async def post_image(self, to_wxid, image_url: str):
+        payload = {
+            "appId": self.appid,
+            "toWxid": to_wxid,
+            "imgUrl": image_url,
+        }
+        
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{self.base_url}/message/postImage",
+                headers=self.headers,
+                json=payload
+            ) as resp:
+                json_blob = await resp.json()
+                logger.debug(f"发送图片结果: {json_blob}")
+                
+    async def post_voice(self, to_wxid, voice_url: str, voice_duration: int):
+        payload = {
+            "appId": self.appid,
+            "toWxid": to_wxid,
+            "voiceUrl": voice_url,
+            "voiceDuration": voice_duration
+        }
+        
+        logger.debug(f"发送语音: {payload}")
+        
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{self.base_url}/message/postVoice",
+                headers=self.headers,
+                json=payload
+            ) as resp:
+                json_blob = await resp.json()
+                logger.debug(f"发送语音结果: {json_blob}")

astrbot/core/platform/sources/gewechat/downloader.py

@@ -0,0 +1,51 @@
+from astrbot import logger
+import aiohttp
+import json
+
+class GeweDownloader():
+    def __init__(self, base_url: str, download_base_url: str, token: str):
+        self.base_url = base_url
+        self.download_base_url = download_base_url
+        self.headers = {
+            "Content-Type": "application/json",
+            "X-GEWE-TOKEN": token
+        }
+    
+    async def _post_json(self, baseurl: str, route: str, payload: dict):
+        async with aiohttp.ClientSession() as session:
+            async with session.post(
+                f"{baseurl}{route}",
+                headers=self.headers,
+                json=payload
+            ) as resp:
+                return await resp.read()
+            
+    async def download_voice(self, appid: str, xml: str, msg_id: str):
+        payload = {
+            "appId": appid,
+            "xml": xml,
+            "msgId": msg_id
+        }
+        return await self._post_json(self.base_url, "/message/downloadVoice", payload)
+    
+    async def download_image(self, appid: str, xml: str) -> str:
+        '''返回一个可下载的 URL'''
+        choices = [2, 3] #  2:常规图片 3:缩略图
+        
+        for choice in choices:
+            try:
+                payload = {
+                    "appId": appid,
+                    "xml": xml,
+                    "type": choice
+                }
+                data = await self._post_json(self.base_url, "/message/downloadImage", payload)
+                json_blob = json.loads(data)
+                if 'fileUrl' in json_blob['data']:
+                    return self.download_base_url + json_blob['data']['fileUrl']
+
+            except BaseException as e:
+                logger.error(f"gewe download image: {e}")
+                continue
+        
+        raise Exception("无法下载图片")

astrbot/core/platform/sources/gewechat/gewechat_event.py

@@ -1,12 +1,24 @@
-import random
-import asyncio
-from astrbot.core.utils.io import download_image_by_url
+import wave
+import uuid
+import os
+from astrbot.core.utils.io import save_temp_img, download_image_by_url, download_file
+from astrbot.core.utils.tencent_record_helper import wav_to_tencent_silk
 from astrbot.api import logger
 from astrbot.api.event import AstrMessageEvent, MessageChain
 from astrbot.api.platform import AstrBotMessage, PlatformMetadata
-from astrbot.api.message_components import Plain, Image
+from astrbot.api.message_components import Plain, Image, Record
 from .client import SimpleGewechatClient
 
+def get_wav_duration(file_path):
+    with wave.open(file_path, 'rb') as wav_file:
+        file_size = os.path.getsize(file_path)
+        n_channels, sampwidth, framerate, n_frames = wav_file.getparams()[:4]
+        if n_frames == 2147483647:
+            duration = (file_size - 44) / (n_channels * sampwidth * framerate)
+        else:
+            duration = n_frames / float(framerate)
+        return duration
+
 class GewechatPlatformEvent(AstrMessageEvent):
     def __init__(
             self, 
@@ -34,5 +46,57 @@ class GewechatPlatformEvent(AstrMessageEvent):
         for comp in message.chain:
             if isinstance(comp, Plain):
                 await self.client.post_text(to_wxid, comp.text)
-        
+            elif isinstance(comp, Image):
+                img_url = comp.file
+                img_path = ""
+                if img_url.startswith("file:///"):
+                    img_path = img_url[8:]
+                elif comp.file and comp.file.startswith("http"):
+                    img_path = await download_image_by_url(comp.file)
+                else:
+                    img_path = img_url
+                    
+                # 检查 record_path 是否在 data/temp 目录中, record_path 可能是绝对路径
+                temp_directory = os.path.abspath('data/temp')
+                img_path = os.path.abspath(img_path)
+                if os.path.commonpath([temp_directory, img_path]) != temp_directory:
+                    with open(img_path, "rb") as f:
+                        img_path = save_temp_img(f.read())
+
+                file_id = os.path.basename(img_path)
+                img_url = f"{self.client.file_server_url}/{file_id}"
+                logger.debug(f"gewe callback img url: {img_url}")
+                await self.client.post_image(to_wxid, img_url)
+            elif isinstance(comp, Record):
+                # 默认已经存在 data/temp 中
+                record_url = comp.file
+                record_path = ""
+                
+                if record_url.startswith("file:///"):
+                    record_path = record_url[8:]
+                elif record_url.startswith("http"):
+                    await download_file(record_url, f"data/temp/{uuid.uuid4()}.wav")
+                else:
+                    record_path = record_url
+                    
+                silk_path = f"data/temp/{uuid.uuid4()}.silk"
+                duration = await wav_to_tencent_silk(record_path, silk_path)
+                
+                print(f"duration: {duration}, {silk_path}")
+                
+                # 检查 record_path 是否在 data/temp 目录中, record_path 可能是绝对路径
+                # temp_directory = os.path.abspath('data/temp')
+                # record_path = os.path.abspath(record_path)
+                # if os.path.commonpath([temp_directory, record_path]) != temp_directory:
+                #     with open(record_path, "rb") as f:
+                #         record_path = f"data/temp/{uuid.uuid4()}.wav"
+                #         with open(record_path, "wb") as f2:
+                #             f2.write(f.read())
+                
+                if duration == 0:
+                    duration = get_wav_duration(record_path)
+                
+                file_id = os.path.basename(silk_path)
+                record_url = f"{self.client.file_server_url}/{file_id}"
+                await self.client.post_voice(to_wxid, record_url, duration*1000)
         await super().send(message)

astrbot/core/platform/sources/qqofficial/qqofficial_message_event.py

@@ -14,12 +14,20 @@ class QQOfficialMessageEvent(AstrMessageEvent):
     def __init__(self, message_str: str, message_obj: AstrBotMessage, platform_meta: PlatformMetadata, session_id: str, bot: Client):
         super().__init__(message_str, message_obj, platform_meta, session_id)
         self.bot = bot
+        self.send_buffer = None
         
     async def send(self, message: MessageChain):
+        if not self.send_buffer:
+            self.send_buffer = message
+        else:
+            self.send_buffer.chain.extend(message.chain)
+
+    async def _post_send(self):
+        '''QQ 官方 API 仅支持回复一次'''
         source = self.message_obj.raw_message
         assert isinstance(source, (botpy.message.Message, botpy.message.GroupMessage, botpy.message.DirectMessage, botpy.message.C2CMessage))
         
-        plain_text, image_base64, image_path = await QQOfficialMessageEvent._parse_to_qqofficial(message)
+        plain_text, image_base64, image_path = await QQOfficialMessageEvent._parse_to_qqofficial(self.send_buffer)
         
         payload = {
             'content': plain_text,
@@ -48,7 +56,9 @@ class QQOfficialMessageEvent(AstrMessageEvent):
                     payload['file_image'] = image_path
                 await self.bot.api.post_dms(guild_id=source.guild_id, **payload)
 
-        await super().send(message)
+        await super().send(self.send_buffer)
+        
+        self.send_buffer = None
             
     async def upload_group_and_c2c_image(self, image_base64: str, file_type: int, **kwargs) -> botpy.types.message.Media:
         payload = {
@@ -80,4 +90,7 @@ class QQOfficialMessageEvent(AstrMessageEvent):
                 elif i.file and i.file.startswith("http"):
                     image_file_path = await download_image_by_url(i.file)
                     image_base64 = file_to_base64(image_file_path).replace("base64://", "")
+                else:
+                    image_base64 = file_to_base64(i.file).replace("base64://", "")
+                    image_file_path = i.file
         return plain_text, image_base64, image_file_path

astrbot/core/platform/sources/webchat/webchat_event.py

@@ -32,6 +32,10 @@ class WebChatMessageEvent(AstrMessageEvent):
                             f.write(f2.read())
                 elif comp.file and comp.file.startswith("http"):
                     await download_image_by_url(comp.file, path=path)
+                else:
+                    with open(path, "wb") as f:
+                        with open(comp.file, "rb") as f2:
+                            f.write(f2.read())
                 web_chat_back_queue.put_nowait((f"[IMAGE]{filename}", cid))
         web_chat_back_queue.put_nowait(None)
         await super().send(message)

astrbot/core/provider/manager.py

@@ -1,6 +1,6 @@
 import traceback
 from astrbot.core.config.astrbot_config import AstrBotConfig
-from .provider import Provider, STTProvider, Personality
+from .provider import Provider, STTProvider, TTSProvider, Personality
 from .entites import ProviderType
 from typing import List
 from astrbot.core.db import BaseDatabase
@@ -64,11 +64,15 @@ class ProviderManager():
         '''加载的 Provider 的实例'''
         self.stt_provider_insts: List[STTProvider] = []
         '''加载的 Speech To Text Provider 的实例'''
+        self.tts_provider_insts: List[TTSProvider] = []
+        '''加载的 Text To Speech Provider 的实例'''
         self.llm_tools = llm_tools
         self.curr_provider_inst: Provider = None
         '''当前使用的 Provider 实例'''
         self.curr_stt_provider_inst: STTProvider = None
         '''当前使用的 Speech To Text Provider 实例'''
+        self.curr_tts_provider_inst: TTSProvider = None
+        '''当前使用的 Text To Speech Provider 实例'''
         self.loaded_ids = defaultdict(bool)
         self.db_helper = db_helper
         
@@ -103,6 +107,8 @@ class ProviderManager():
                         from .sources.whisper_api_source import ProviderOpenAIWhisperAPI # noqa: F401
                     case "openai_whisper_selfhost":
                         from .sources.whisper_selfhosted_source import ProviderOpenAIWhisperSelfHost # noqa: F401
+                    case "openai_tts_api":
+                        from .sources.openai_tts_api_source import ProviderOpenAITTSAPI # noqa: F401
             except (ImportError, ModuleNotFoundError) as e:
                 logger.critical(f"加载 {provider_cfg['type']}({provider_cfg['id']}) 提供商适配器失败：{e}。可能是因为有未安装的依赖。")
                 continue
@@ -111,17 +117,21 @@ class ProviderManager():
                 continue
             
     async def initialize(self):
+        
+        selected_provider_id = sp.get("curr_provider")
+        selected_stt_provider_id = self.provider_stt_settings.get("provider_id")
+        selected_tts_provider_id = self.provider_settings.get("provider_id")
+        provider_enabled = self.provider_settings.get("enable", False)
+        stt_enabled = self.provider_stt_settings.get("enable", False)
+        tts_enabled = self.provider_settings.get("enable", False)
+            
         for provider_config in self.providers_config:
             if not provider_config['enable']:
                 continue
             if provider_config['type'] not in provider_cls_map:
                 logger.error(f"未找到适用于 {provider_config['type']}({provider_config['id']}) 的提供商适配器，请检查是否已经安装或者名称填写错误。已跳过。")
                 continue
-            selected_provider_id = sp.get("curr_provider")
-            selected_stt_provider_id = self.provider_stt_settings.get("provider_id")
-            provider_enabled = self.provider_settings.get("enable", False)
-            stt_enabled = self.provider_stt_settings.get("enable", False)
-            
+
             provider_metadata = provider_cls_map[provider_config['type']]
             logger.info(f"尝试实例化 {provider_config['type']}({provider_config['id']}) 提供商适配器 ...")
             try:
@@ -138,6 +148,18 @@ class ProviderManager():
                     if selected_stt_provider_id == provider_config['id'] and stt_enabled:
                         self.curr_stt_provider_inst = inst
                         logger.info(f"已选择 {provider_config['type']}({provider_config['id']}) 作为当前语音转文本提供商适配器。")
+                        
+                elif provider_metadata.provider_type == ProviderType.TEXT_TO_SPEECH:
+                    # TTS 任务
+                    inst = provider_metadata.cls_type(provider_config, self.provider_settings)
+                    
+                    if getattr(inst, "initialize", None):
+                        await inst.initialize()
+                    
+                    self.tts_provider_insts.append(inst)
+                    if selected_tts_provider_id == provider_config['id'] and tts_enabled:
+                        self.curr_tts_provider_inst = inst
+                        logger.info(f"已选择 {provider_config['type']}({provider_config['id']}) 作为当前文本转语音提供商适配器。")
                     
                 elif provider_metadata.provider_type == ProviderType.CHAT_COMPLETION:
                     # 文本生成任务
@@ -167,11 +189,18 @@ class ProviderManager():
         if len(self.stt_provider_insts) > 0 and not self.curr_stt_provider_inst and stt_enabled:
             self.curr_stt_provider_inst = self.stt_provider_insts[0]
             
+        if len(self.tts_provider_insts) > 0 and not self.curr_tts_provider_inst and tts_enabled:
+            self.curr_tts_provider_inst = self.tts_provider_insts[0]
+            
         if not self.curr_provider_inst:
             logger.warning("未启用任何用于 文本生成 的提供商适配器。")
-        if self.provider_stt_settings.get("enable"):
-            if not self.curr_stt_provider_inst:
+            
+        if stt_enabled and not self.curr_stt_provider_inst:
                 logger.warning("未启用任何用于 语音转文本 的提供商适配器。")
+        
+        if tts_enabled and not self.curr_tts_provider_inst:
+                logger.warning("未启用任何用于 文本转语音 的提供商适配器。")
+        
 
     def get_insts(self):
         return self.provider_insts

astrbot/core/provider/provider.py

@@ -24,9 +24,32 @@ class ProviderMeta():
     id: str
     model: str
     type: str
+    
+    
+class AbstractProvider(abc.ABC):
+    def __init__(self, provider_config: dict) -> None:
+        super().__init__()
+        self.model_name = ""
+        self.provider_config = provider_config
+
+    def set_model(self, model_name: str):
+        '''设置当前使用的模型名称'''
+        self.model_name = model_name
+    
+    def get_model(self) -> str:
+        '''获得当前使用的模型名称'''
+        return self.model_name
+    
+    def meta(self) -> ProviderMeta:
+        '''获取 Provider 的元数据'''
+        return ProviderMeta(
+            id=self.provider_config['id'],
+            model=self.get_model(),
+            type=self.provider_config['type']
+        )
 
 
-class Provider(abc.ABC):
+class Provider(AbstractProvider):
     def __init__(
         self, 
         provider_config: dict,
@@ -35,14 +58,11 @@ class Provider(abc.ABC):
         db_helper: BaseDatabase = None,
         default_persona: Personality = None
     ) -> None:
-        self.model_name = ""
-        '''当前使用的模型名称'''
+        super().__init__(provider_config)
         
         self.session_memory = defaultdict(list)
         '''维护了 session_id 的上下文，**不包含 system 指令**。'''
         
-        self.provider_config = provider_config
-        
         self.provider_settings = provider_settings
         
         self.curr_personality: Personality = default_persona
@@ -58,14 +78,6 @@ class Provider(abc.ABC):
                     self.session_memory[history.session_id] = json.loads(history.content)
             except BaseException as e:
                 logger.warning(f"读取 LLM 对话历史记录 失败：{e}。仍可正常使用。")
-
-    def set_model(self, model_name: str):
-        '''设置当前使用的模型名称'''
-        self.model_name = model_name
-    
-    def get_model(self) -> str:
-        '''获得当前使用的模型名称'''
-        return self.model_name
     
     @abc.abstractmethod
     def get_current_key(self) -> str:
@@ -133,17 +145,11 @@ class Provider(abc.ABC):
         '''重置某一个 session_id 的上下文'''
         raise NotImplementedError()
 
-    def meta(self) -> ProviderMeta:
-        '''获取 Provider 的元数据'''
-        return ProviderMeta(
-            id=self.provider_config['id'],
-            model=self.get_model(),
-            type=self.provider_config['type']
-        )
+
         
-        
-class STTProvider():
+class STTProvider(AbstractProvider):
     def __init__(self, provider_config: dict, provider_settings: dict) -> None:
+        super().__init__(provider_config)
         self.provider_config = provider_config
         self.provider_settings = provider_settings
     
@@ -151,19 +157,15 @@ class STTProvider():
     async def get_text(self, audio_url: str) -> str:
         '''获取音频的文本'''
         raise NotImplementedError()
+
+
+class TTSProvider(AbstractProvider):
+    def __init__(self, provider_config: dict, provider_settings: dict) -> None:
+        super().__init__(provider_config)
+        self.provider_config = provider_config
+        self.provider_settings = provider_settings
     
-    def set_model(self, model_name: str):
-        '''设置当前使用的模型名称'''
-        self.model_name = model_name
-    
-    def get_model(self) -> str:
-        '''获取当前使用的模型'''
-        return self.provider_config.get("model", "")
-    
-    def meta(self) -> ProviderMeta:
-        '''获取 Provider 的元数据'''
-        return ProviderMeta(
-            id=self.provider_config['id'],
-            model=self.get_model(),
-            type=self.provider_config['type']
-        )
+    @abc.abstractmethod
+    async def get_audio(self, text: str) -> str:
+        '''获取文本的音频，返回音频文件路径'''
+        raise NotImplementedError()

astrbot/core/provider/register.py

@@ -28,6 +28,8 @@ def register_provider_adapter(
                 default_config_tmpl['type'] = provider_type_name
             if 'enable' not in default_config_tmpl:
                 default_config_tmpl['enable'] = False
+            if 'id' not in default_config_tmpl:
+                default_config_tmpl['id'] = provider_type_name
 
         pm = ProviderMetaData(
             type=provider_type_name,

astrbot/core/provider/sources/openai_source.py

@@ -1,4 +1,3 @@
-import traceback
 import base64
 import json
 
@@ -110,7 +109,7 @@ class ProviderOpenAIOfficial(Provider):
         )
         
         assert isinstance(completion, ChatCompletion)
-        logger.debug(f"completion: {completion.usage}")
+        logger.debug(f"completion: {completion}")
 
         if len(completion.choices) == 0:
             raise Exception("API 返回的 completion 为空。")

astrbot/core/provider/sources/openai_tts_api_source.py

@@ -0,0 +1,40 @@
+import uuid
+import os
+from openai import AsyncOpenAI, NOT_GIVEN
+from ..provider import TTSProvider
+from ..entites import ProviderType
+from ..register import register_provider_adapter
+
+
+@register_provider_adapter("openai_tts_api", "OpenAI TTS API", provider_type=ProviderType.TEXT_TO_SPEECH)
+class ProviderOpenAITTSAPI(TTSProvider):
+    def __init__(
+        self, 
+        provider_config: dict, 
+        provider_settings: dict,
+    ) -> None:
+        super().__init__(provider_config, provider_settings)
+        self.chosen_api_key = provider_config.get("api_key", "")
+        self.voice = provider_config.get("voice", "alloy")
+
+        self.client = AsyncOpenAI(
+            api_key=self.chosen_api_key,
+            base_url=provider_config.get("api_base", None),
+            timeout=provider_config.get("timeout", NOT_GIVEN),
+        )
+        
+        self.set_model(provider_config.get("model", None))
+
+
+    async def get_audio(self, text: str) -> str:
+        path = f'data/temp/openai_tts_api_{uuid.uuid4()}.wav'
+        async with self.client.audio.speech.with_streaming_response.create(
+            model=self.model_name,
+            voice=self.voice,
+            response_format='wav',
+            input=text
+        ) as response:
+            with open(path, 'wb') as f:
+                async for chunk in response.iter_bytes(chunk_size=1024):
+                    f.write(chunk)
+        return path

astrbot/core/provider/sources/whisper_api_source.py

@@ -1,12 +1,12 @@
 import uuid
 import os
-import io
 from openai import AsyncOpenAI, NOT_GIVEN
 from ..provider import STTProvider
 from ..entites import ProviderType
 from astrbot.core.utils.io import download_file
 from ..register import register_provider_adapter
 from astrbot.core import logger
+from astrbot.core.utils.tencent_record_helper import tencent_silk_to_wav
 
 @register_provider_adapter("openai_whisper_api", "OpenAI Whisper API", provider_type=ProviderType.SPEECH_TO_TEXT)
 class ProviderOpenAIWhisperAPI(STTProvider):
@@ -33,34 +33,6 @@ class ProviderOpenAIWhisperAPI(STTProvider):
         output_path = ff.convert(path, os.path.join('data/temp', filename))
         return output_path
     
-    async def _pcm_to_wav(self, input_io: io.BytesIO, output_path: str) -> str:
-        import wave
-        
-        with wave.open(output_path, 'wb') as wav:
-            wav.setnchannels(1)
-            wav.setsampwidth(2)
-            wav.setframerate(24000)
-            wav.writeframes(input_io.read())
-            
-        return output_path
-
-    async def _convert_silk(self, path: str) -> str:
-        import pysilk
-        filename = str(uuid.uuid4()) + '.wav'
-        output_path = os.path.join('data/temp', filename)
-        with open(path, "rb") as f:
-            input_data = f.read()
-            if input_data.startswith(b'\x02'):
-                # tencent 我爱你
-                input_data = input_data[1:]
-            input_io = io.BytesIO(input_data)
-            output_io = io.BytesIO()
-            pysilk.decode(input_io, output_io, 24000)
-            output_io.seek(0)
-            await self._pcm_to_wav(output_io, output_path)
-        
-        return output_path
-    
     async def _is_silk_file(self, file_path):
         silk_header = b"SILK"
         with open(file_path, "rb") as f:
@@ -91,8 +63,9 @@ class ProviderOpenAIWhisperAPI(STTProvider):
             is_silk = await self._is_silk_file(audio_url)
             if is_silk:
                 logger.info("Converting silk file to wav ...")
-                audio_url = await self._convert_silk(audio_url)
-
+                output_path = os.path.join('data/temp', str(uuid.uuid4()) + '.wav')
+                await tencent_silk_to_wav(audio_url, output_path)
+                audio_url = output_path
         
         result = await self.client.audio.transcriptions.create(
             model=self.model_name,

astrbot/core/provider/sources/whisper_selfhosted_source.py

@@ -1,6 +1,5 @@
 import uuid
 import os
-import io
 import asyncio
 import whisper
 from ..provider import STTProvider
@@ -8,7 +7,7 @@ from ..entites import ProviderType
 from astrbot.core.utils.io import download_file
 from ..register import register_provider_adapter
 from astrbot.core import logger
-
+from astrbot.core.utils.tencent_record_helper import tencent_silk_to_wav
 
 @register_provider_adapter("openai_whisper_selfhost", "OpenAI Whisper 模型部署", provider_type=ProviderType.SPEECH_TO_TEXT)
 class ProviderOpenAIWhisperSelfHost(STTProvider):
@@ -34,34 +33,6 @@ class ProviderOpenAIWhisperSelfHost(STTProvider):
         output_path = ff.convert(path, os.path.join('data/temp', filename))
         return output_path
     
-    async def _pcm_to_wav(self, input_io: io.BytesIO, output_path: str) -> str:
-        import wave
-        
-        with wave.open(output_path, 'wb') as wav:
-            wav.setnchannels(1)
-            wav.setsampwidth(2)
-            wav.setframerate(24000)
-            wav.writeframes(input_io.read())
-            
-        return output_path
-
-    async def _convert_silk(self, path: str) -> str:
-        import pysilk
-        filename = str(uuid.uuid4()) + '.wav'
-        output_path = os.path.join('data/temp', filename)
-        with open(path, "rb") as f:
-            input_data = f.read()
-            if input_data.startswith(b'\x02'):
-                # tencent 我爱你
-                input_data = input_data[1:]
-            input_io = io.BytesIO(input_data)
-            output_io = io.BytesIO()
-            pysilk.decode(input_io, output_io, 24000)
-            output_io.seek(0)
-            await self._pcm_to_wav(output_io, output_path)
-        
-        return output_path
-    
     async def _is_silk_file(self, file_path):
         silk_header = b"SILK"
         with open(file_path, "rb") as f:
@@ -93,7 +64,9 @@ class ProviderOpenAIWhisperSelfHost(STTProvider):
             is_silk = await self._is_silk_file(audio_url)
             if is_silk:
                 logger.info("Converting silk file to wav ...")
-                audio_url = await self._convert_silk(audio_url)
-
+                output_path = os.path.join('data/temp', str(uuid.uuid4()) + '.wav')
+                await tencent_silk_to_wav(audio_url, output_path)
+                audio_url = output_path
+                
         result = await loop.run_in_executor(None, self.model.transcribe, audio_url)
         return result['text']

astrbot/core/utils/io.py

@@ -6,6 +6,8 @@ import time
 import aiohttp
 import base64
 import zipfile
+import uuid
+from typing import Union
 
 from PIL import Image
 
@@ -41,21 +43,21 @@ def port_checker(port: int, host: str = "localhost"):
         return False
     
 
-def save_temp_img(img: Image) -> str:
+def save_temp_img(img: Union[Image.Image, str]) -> str:
     os.makedirs("data/temp", exist_ok=True)
-    # 获得文件创建时间，清除超过1小时的
+    # 获得文件创建时间，清除超过 12 小时的
     try:
         for f in os.listdir("data/temp"):
             path = os.path.join("data/temp", f)
             if os.path.isfile(path):
                 ctime = os.path.getctime(path)
-                if time.time() - ctime > 3600:
+                if time.time() - ctime > 3600*12:
                     os.remove(path)
     except Exception as e:
         print(f"清除临时文件失败: {e}")
 
     # 获得时间戳
-    timestamp = int(time.time())
+    timestamp = f"{int(time.time())}_{uuid.uuid4().hex[:8]}"
     p = f"data/temp/{timestamp}.jpg"
 
     if isinstance(img, Image.Image):

astrbot/core/utils/tencent_record_helper.py

@@ -0,0 +1,42 @@
+import wave
+from io import BytesIO
+
+async def tencent_silk_to_wav(silk_path: str, output_path: str) -> str:
+    import pysilk
+    
+    with open(silk_path, "rb") as f:
+        input_data = f.read()
+        if input_data.startswith(b'\x02'):
+            input_data = input_data[1:]
+        input_io = BytesIO(input_data)
+        output_io = BytesIO()
+        pysilk.decode(input_io, output_io, 24000)
+        output_io.seek(0)
+        with wave.open(output_path, 'wb') as wav:
+            wav.setnchannels(1)
+            wav.setsampwidth(2)
+            wav.setframerate(24000)
+            wav.writeframes(output_io.read())
+        
+    return output_path
+
+async def wav_to_tencent_silk(wav_path: str, output_path: str) -> int:
+    '''返回 duration'''
+    import pysilk
+
+    with wave.open(wav_path, 'rb') as wav:
+        wav_data = wav.readframes(wav.getnframes())
+        wav_data = BytesIO(wav_data)
+        output_io = BytesIO()
+        pysilk.encode(wav_data, output_io, 24000, 24000)
+        output_io.seek(0)
+        
+        # 在首字节添加 \x02,去除结尾的\xff\xff
+        silk_data = output_io.read()
+        silk_data_with_prefix = b'\x02' + silk_data[:-2]
+        
+        # return BytesIO(silk_data_with_prefix)
+        with open(output_path, "wb") as f:
+            f.write(silk_data_with_prefix)
+            
+        return 0

astrbot/dashboard/routes/update.py

@@ -1,14 +1,14 @@
-import threading
 import traceback
 from .route import Route, Response, RouteContext
 from quart import request
+from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
 from astrbot.core.updator import AstrBotUpdator
 from astrbot.core import logger, pip_installer
 from astrbot.core.utils.io import download_dashboard, get_dashboard_version
 from astrbot.core.config.default import VERSION
 
 class UpdateRoute(Route):
-    def __init__(self, context: RouteContext, astrbot_updator: AstrBotUpdator) -> None:
+    def __init__(self, context: RouteContext, astrbot_updator: AstrBotUpdator, core_lifecycle: AstrBotCoreLifecycle) -> None:
         super().__init__(context)
         self.routes = {
             '/update/check': ('GET', self.check_update),
@@ -17,6 +17,7 @@ class UpdateRoute(Route):
             '/update/pip-install': ('POST', self.install_pip_package)
         }
         self.astrbot_updator = astrbot_updator
+        self.core_lifecycle = core_lifecycle
         self.register_routes()
     
     async def check_update(self):
@@ -62,9 +63,17 @@ class UpdateRoute(Route):
                     await download_dashboard()
                 except Exception as e:
                     logger.error(f"下载管理面板文件失败: {e}。")
+                    
+            # pip 更新依赖
+            logger.info("更新依赖中...")
+            try:
+                pip_installer.install(requirements_path="requirements.txt")
+            except Exception as e:
+                logger.error(f"更新依赖失败: {e}")
             
             if reboot:
-                threading.Thread(target=self.astrbot_updator._reboot, args=(2, )).start()
+                # threading.Thread(target=self.astrbot_updator._reboot, args=(2, )).start()
+                self.core_lifecycle.restart()
                 return Response().ok(None, "更新成功，AstrBot 将在 2 秒内全量重启以应用新的代码。").__dict__
             else:
                 return Response().ok(None, "更新成功，AstrBot 将在下次启动时应用新的代码。").__dict__

astrbot/dashboard/server.py

@@ -24,7 +24,7 @@ class AstrBotDashboard():
         # token 用于验证请求
         logging.getLogger(self.app.name).removeHandler(default_handler)
         self.context = RouteContext(self.config, self.app)
-        self.ur = UpdateRoute(self.context, core_lifecycle.astrbot_updator)
+        self.ur = UpdateRoute(self.context, core_lifecycle.astrbot_updator, core_lifecycle)
         self.sr = StatRoute(self.context, db, core_lifecycle)
         self.pr = PluginRoute(self.context, core_lifecycle, core_lifecycle.plugin_manager)
         self.cr = ConfigRoute(self.context, core_lifecycle)

changelogs/v3.4.11.md

@@ -0,0 +1,6 @@
+# What's Changed
+
+- 为平台和提供商适配器添加默认 ID 配置 #248
+- 修复appid保存的问题和部分群聊at失效的问题和群聊@的sender username显示异常的问题
+- 优化更新项目时重启可能会导致Address already in use的问题
+- 各类异步任务报错后的优雅报错输出，而不是只有在退出程序的时候才输出异常日志。

changelogs/v3.4.12.md

@@ -0,0 +1,6 @@
+# What's Changed
+
+- Gewechat 微信支持图片、语音的收和发
+- 支持 OpenAI TTS（文字转语音）
+- 支持路径映射，解决 docker 部署时两端文件系统不一致导致的富媒体文件路径不存在问题
+- Napcat 下语音消息可能接收异常

changelogs/v3.4.13.md

@@ -0,0 +1,4 @@
+# What's Changed
+
+- 修复 astrbot_updator 属性缺失与stt_enabled 未初始化 #252
+- 支持消息分段回复

dashboard/src/views/dashboards/default/DefaultDashboard.vue

@@ -1,4 +1,13 @@
 <template>
+  <v-row style="margin: 2px;">
+    <v-alert
+      :type="noticeType"
+      :text="noticeContent"
+      :title="noticeTitle"
+      v-if="noticeTitle && noticeContent"
+      closable
+    ></v-alert>
+  </v-row>
   <v-row>
     <v-col cols="12" md="4">
       <TotalMessage :stat="stat" />
@@ -38,13 +47,26 @@ export default {
   },
   data: () => ({
     stat: {},
+    noticeTitle: '',
+    noticeContent: '',
+    noticeType: '',
   }),
 
   mounted() {
     axios.get('/api/stat/get').then((res) => {
       this.stat = res.data.data;
     });
-  }
+
+    axios.get('https://api.soulter.top/astrbot-announcement').then((res) => {
+      let data = res.data.data;
+      // 如果 dashboard-notice 在其中
+      if (data['dashboard-notice']) {
+        this.noticeTitle = data['dashboard-notice'].title;
+        this.noticeContent = data['dashboard-notice'].content;
+        this.noticeType = data['dashboard-notice'].type;
+      }
+    });
+  },
 };
 
 </script>