feat(wechatcomapp): add support for splitting long audio files

channel/wechatcom/wechatcomapp_channel.py

@@ -19,7 +19,7 @@ from common.log import logger
 from common.singleton import singleton
 from common.utils import compress_imgfile, fsize, split_string_by_utf8_length
 from config import conf, subscribe_msg
-from voice.audio_convert import any_to_amr
+from voice.audio_convert import any_to_amr, split_audio
 
 MAX_UTF8_LEN = 2048
 
@@ -66,8 +66,12 @@ class WechatComAppChannel(ChatChannel):
                 file_path = reply.content
                 amr_file = os.path.splitext(file_path)[0] + ".amr"
                 any_to_amr(file_path, amr_file)
-                response = self.client.media.upload("voice", open(amr_file, "rb"))
-                logger.debug("[wechatcom] upload voice response: {}".format(response))
+                files = split_audio(amr_file, 60000)
+                if len(files) > 1:
+                    logger.info("[wechatcom] voice too long, split into {} parts".format(len(files)))
+                for path in files:
+                    response = self.client.media.upload("voice", open(path, "rb"))
+                    logger.debug("[wechatcom] upload voice response: {}".format(response))
             except WeChatClientException as e:
                 logger.error("[wechatcom] upload voice failed: {}".format(e))
                 return

voice/audio_convert.py

@@ -92,6 +92,7 @@ def any_to_amr(any_path, amr_path):
     audio = AudioSegment.from_file(any_path)
     audio = audio.set_frame_rate(8000)  # only support 8000
     audio.export(amr_path, format="amr")
+    return audio.duration_seconds * 1000
 
 
 def sil_to_wav(silk_path, wav_path, rate: int = 24000):
@@ -101,3 +102,26 @@ def sil_to_wav(silk_path, wav_path, rate: int = 24000):
     wav_data = pysilk.decode_file(silk_path, to_wav=True, sample_rate=rate)
     with open(wav_path, "wb") as f:
         f.write(wav_data)
+
+
+def split_audio(file_path, max_segment_length_ms=60000):
+    """
+    分割音频文件
+    """
+    audio = AudioSegment.from_file(file_path)
+    audio_length_ms = len(audio)
+    if audio_length_ms <= max_segment_length_ms:
+        return [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)
+        segment = audio[start_ms:end_ms]
+        segments.append(segment)
+    file_prefix = file_path[: file_path.rindex(".")]
+    format = file_path[file_path.rindex(".") + 1 :]
+    files = []
+    for i, segment in enumerate(segments):
+        path = f"{file_prefix}_{i+1}" + f".{format}"
+        segment.export(path, format=format)
+        files.append(path)
+    return files