From fb22e01b89f37ac41223ef167853b0c8e709500c Mon Sep 17 00:00:00 2001
From: lanvent <lanvent@qq.com>
Date: Thu, 27 Apr 2023 23:04:24 +0800
Subject: [PATCH] fix: send voice in wechatcomapp rightly

---
 channel/wechatcom/wechatcomapp_channel.py | 10 +++++++---
 voice/audio_convert.py                    |  4 ++--
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/channel/wechatcom/wechatcomapp_channel.py b/channel/wechatcom/wechatcomapp_channel.py
index a79ca65..72804e4 100644
--- a/channel/wechatcom/wechatcomapp_channel.py
+++ b/channel/wechatcom/wechatcomapp_channel.py
@@ -63,15 +63,17 @@ class WechatComAppChannel(ChatChannel):
             logger.info("[wechatcom] Do send text to {}: {}".format(receiver, reply_text))
         elif reply.type == ReplyType.VOICE:
             try:
+                media_ids = []
                 file_path = reply.content
                 amr_file = os.path.splitext(file_path)[0] + ".amr"
                 any_to_amr(file_path, amr_file)
-                files = split_audio(amr_file, 60000)
+                duration, files = split_audio(amr_file, 60 * 1000)
                 if len(files) > 1:
-                    logger.info("[wechatcom] voice too long, split into {} parts".format(len(files)))
+                    logger.info("[wechatcom] voice too long {}s > 60s , split into {} parts".format(duration / 1000.0, len(files)))
                 for path in files:
                     response = self.client.media.upload("voice", open(path, "rb"))
                     logger.debug("[wechatcom] upload voice response: {}".format(response))
+                    media_ids.append(response["media_id"])
             except WeChatClientException as e:
                 logger.error("[wechatcom] upload voice failed: {}".format(e))
                 return
@@ -81,7 +83,9 @@ class WechatComAppChannel(ChatChannel):
                     os.remove(amr_file)
             except Exception:
                 pass
-            self.client.message.send_voice(self.agent_id, receiver, response["media_id"])
+            for media_id in media_ids:
+                self.client.message.send_voice(self.agent_id, receiver, media_id)
+                time.sleep(1)
             logger.info("[wechatcom] sendVoice={}, receiver={}".format(reply.content, receiver))
         elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
             img_url = reply.content
diff --git a/voice/audio_convert.py b/voice/audio_convert.py
index 4b72d6b..9c9515a 100644
--- a/voice/audio_convert.py
+++ b/voice/audio_convert.py
@@ -111,7 +111,7 @@ def split_audio(file_path, max_segment_length_ms=60000):
     audio = AudioSegment.from_file(file_path)
     audio_length_ms = len(audio)
     if audio_length_ms <= max_segment_length_ms:
-        return [file_path]
+        return audio_length_ms, [file_path]
     segments = []
     for start_ms in range(0, audio_length_ms, max_segment_length_ms):
         end_ms = min(audio_length_ms, start_ms + max_segment_length_ms)
@@ -124,4 +124,4 @@ def split_audio(file_path, max_segment_length_ms=60000):
         path = f"{file_prefix}_{i+1}" + f".{format}"
         segment.export(path, format=format)
         files.append(path)
-    return files
+    return audio_length_ms, files