Merge pull request #1737 from zhx8702/feat-wehcatpro-voice-adapter

feat: wechatpadpro 添加语音接收和发送的适配

astrbot/core/platform/sources/wechatpadpro/wechatpadpro_adapter.py

@@ -1,13 +1,15 @@
 import asyncio
+import base64
 import json
 import os
 import time
 from typing import Optional
 
 import aiohttp
+import anyio
 import websockets
 from astrbot import logger
-from astrbot.api.message_components import Plain, Image, At
+from astrbot.api.message_components import Plain, Image, At, Record
 from astrbot.api.platform import Platform, PlatformMetadata
 from astrbot.core.message.message_event_result import MessageChain
 from astrbot.core.platform.astrbot_message import (
@@ -581,6 +583,32 @@ class WeChatPadProAdapter(Platform):
                 logger.error(f"下载图片时发生错误: {e}")
                 return None
 
+    async def download_voice(
+        self, to_user_name: str, new_msg_id: str, bufid: str, length: int
+    ):
+        """下载原始音频。"""
+        url = f"{self.base_url}/message/GetMsgVoice"
+        params = {"key": self.auth_key}
+        payload = {
+            "Bufid": bufid,
+            "ToUserName": to_user_name,
+            "NewMsgId": new_msg_id,
+            "Length": length,
+        }
+        async with aiohttp.ClientSession() as session:
+            try:
+                async with session.post(url, params=params, json=payload) as response:
+                    if response.status == 200:
+                        return await response.json()
+                    logger.error(f"下载音频失败: {response.status}")
+                    return None
+            except aiohttp.ClientConnectorError as e:
+                logger.error(f"连接到 WeChatPadPro 服务失败: {e}")
+                return None
+            except Exception as e:
+                logger.error(f"下载音频时发生错误: {e}")
+                return None
+
     async def _process_message_content(
         self, abm: AstrBotMessage, raw_message: dict, msg_type: int, content: str
     ):
@@ -659,8 +687,38 @@ class WeChatPadProAdapter(Platform):
             if emoji_message is not None:
                 abm.message.append(emoji_message)
         elif msg_type == 50:
-            # 语音/视频
             logger.warning("收到语音/视频消息，待实现。")
+        elif msg_type == 34:
+            # 语音消息
+            bufid = 0
+            to_user_name = raw_message.get("to_user_name", {}).get("str", "")
+            new_msg_id = raw_message.get("new_msg_id")
+            data_parser = GeweDataParser(
+                content=content,
+                is_private_chat=(abm.type != MessageType.GROUP_MESSAGE),
+                raw_message=raw_message,
+            )
+
+            voicemsg = data_parser._format_to_xml().find("voicemsg")
+            bufid = voicemsg.get("bufid") or "0"
+            length = int(voicemsg.get("length") or 0)
+            voice_resp = await self.download_voice(
+                to_user_name=to_user_name,
+                new_msg_id=new_msg_id,
+                bufid=bufid,
+                length=length,
+            )
+            voice_bs64_data = voice_resp.get("Data", {}).get("Base64", None)
+            if voice_bs64_data:
+                voice_bs64_data = base64.b64decode(voice_bs64_data)
+                temp_dir = os.path.join(get_astrbot_data_path(), "temp")
+                file_path = os.path.join(
+                    temp_dir, f"wechatpadpro_voice_{abm.message_id}.silk"
+                )
+
+                async with await anyio.open_file(file_path, "wb") as f:
+                    await f.write(voice_bs64_data)
+                abm.message.append(Record(file=file_path, url=file_path))
         elif msg_type == 49:
             try:
                 parser = GeweDataParser(

astrbot/core/platform/sources/wechatpadpro/wechatpadpro_message_event.py

@@ -7,11 +7,17 @@ import aiohttp
 from PIL import Image as PILImage  # 使用别名避免冲突
 
 from astrbot import logger
-from astrbot.core.message.components import Image, Plain, WechatEmoji  # Import Image
+from astrbot.core.message.components import (
+    Image,
+    Plain,
+    WechatEmoji,
+    Record,
+)  # Import Image
 from astrbot.core.message.message_event_result import MessageChain
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from astrbot.core.platform.astrbot_message import AstrBotMessage, MessageType
 from astrbot.core.platform.platform_metadata import PlatformMetadata
+from astrbot.core.utils.tencent_record_helper import wav_to_tencent_silk_base64
 
 if TYPE_CHECKING:
     from .wechatpadpro_adapter import WeChatPadProAdapter
@@ -40,6 +46,8 @@ class WeChatPadProMessageEvent(AstrMessageEvent):
                     await self._send_image(session, comp)
                 elif isinstance(comp, WechatEmoji):
                     await self._send_emoji(session, comp)
+                elif isinstance(comp, Record):
+                    await self._send_voice(session, comp)
         await super().send(message)
 
     async def _send_image(self, session: aiohttp.ClientSession, comp: Image):
@@ -98,6 +106,19 @@ class WeChatPadProMessageEvent(AstrMessageEvent):
         url = f"{self.adapter.base_url}/message/SendEmojiMessage"
         await self._post(session, url, payload)
 
+    async def _send_voice(self, session: aiohttp.ClientSession, comp: Record):
+        record_path = await comp.convert_to_file_path()
+        # 默认已经存在 data/temp 中
+        b64, duration = await wav_to_tencent_silk_base64(record_path)
+        payload = {
+            "ToUserName": self.session_id,
+            "VoiceData": b64,
+            "VoiceFormat": 4,
+            "VoiceSecond": duration,
+        }
+        url = f"{self.adapter.base_url}/message/SendVoice"
+        await self._post(session, url, payload)
+
     @staticmethod
     def _validate_base64(b64: str) -> bytes:
         return base64.b64decode(b64, validate=True)

astrbot/core/utils/tencent_record_helper.py

@@ -1,5 +1,10 @@
+import base64
 import wave
+import os
 from io import BytesIO
+import asyncio
+import tempfile
+from astrbot.core.utils.astrbot_path import get_astrbot_data_path
 
 
 async def tencent_silk_to_wav(silk_path: str, output_path: str) -> str:
@@ -50,3 +55,46 @@ async def wav_to_tencent_silk(wav_path: str, output_path: str) -> int:
         rate = wav.getframerate()
         duration = pilk.encode(wav_path, output_path, pcm_rate=rate, tencent=True)
         return duration
+
+
+async def wav_to_tencent_silk_base64(wav_path: str) -> str:
+    """
+    将 WAV 文件转为 Silk，并返回 Base64 字符串。
+    默认采样率为 24000，输出临时文件为 temp/output.silk。
+
+    参数:
+    - wav_path: 输入 .wav 文件路径（需为 PCM 16bit）
+
+    返回:
+    - Base64 编码的 Silk 字符串
+    - duration: 音频时长（秒）
+    """
+    try:
+        import pilk
+    except ImportError as e:
+        raise Exception("pysilk 模块未安装，请安装 pysilk") from e
+
+    temp_dir = os.path.join(get_astrbot_data_path(), "temp")
+    os.makedirs(temp_dir, exist_ok=True)
+
+    with wave.open(wav_path, "rb") as wav:
+        rate = wav.getframerate()
+
+    with tempfile.NamedTemporaryFile(
+        suffix=".silk", delete=False, dir=temp_dir
+    ) as tmp_file:
+        silk_path = tmp_file.name
+
+    try:
+        duration = await asyncio.to_thread(
+            pilk.encode, wav_path, silk_path, pcm_rate=rate, tencent=True
+        )
+
+        with open(silk_path, "rb") as f:
+            silk_bytes = await asyncio.to_thread(f.read)
+            silk_b64 = base64.b64encode(silk_bytes).decode("utf-8")
+
+        return silk_b64, duration  # 已是秒
+    finally:
+        if os.path.exists(silk_path):
+            os.remove(silk_path)