语音voice出问题error

MewoTrix commented 1 month ago

2024-10-19 05:04:54.170 | INFO | app.services.voice:azure_tts_v1:1057 - start, voice name: zh-CN-shaanxi-XiaoniNeural, try: 1

2024-10-19 05:04:55.217 | ERROR | app.services.voice:azure_tts_v1:1080 - failed, error: 403, message='Invalid response status', url=URL('wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4&ConnectionId=f72db19c54a740b5964bd008ac84f41a')

2024-10-19 05:04:55.218 | INFO | app.services.voice:azure_tts_v1:1057 - start, voice name: zh-CN-shaanxi-XiaoniNeural, try: 2

2024-10-19 05:04:56.168 | ERROR | app.services.voice:azure_tts_v1:1080 - failed, error: 403, message='Invalid response status', url=URL('wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4&ConnectionId=12337f903da44184a919235f1d24a518')

2024-10-19 05:04:56.169 | INFO | app.services.voice:azure_tts_v1:1057 - start, voice name: zh-CN-shaanxi-XiaoniNeural, try: 3

2024-10-19 05:04:57.148 | ERROR | app.services.voice:azure_tts_v1:1080 - failed, error: 403, message='Invalid response status', url=URL('wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4&ConnectionId=22ffe06c3fa1464dbcd1f7d2a98c3c2a')

2024-10-19 05:04:57.149 | ERROR | app.services.task:generate_audio:85 - failed to generate audio:

check if the language of the voice matches the language of the video script.
check if the network is available. If you are in China, it is recommended to use a VPN and enable the global traffic mode.

xushijie commented 1 month ago

我遇到了同样的问题，是这个方法里面的'communicate.stream()' 这个方法抛出来：

  def azure_tts_v1(text: str, voice_name: str, voice_file: str) -> [SubMaker, None]:
      voice_name = parse_voice_name(voice_name)
      text = text.strip()
      for i in range(3):
          try:
              logger.info(f"start, voice name: {voice_name}, try: {i + 1}")

              async def _do() -> SubMaker:
                  communicate = edge_tts.Communicate(text, voice_name)
                  sub_maker = edge_tts.SubMaker()
                  with open(voice_file, "wb") as file:
                      async for chunk in communicate.stream():
                          if chunk["type"] == "audio":
                              file.write(chunk["data"])
                          elif chunk["type"] == "WordBoundary":
                              sub_maker.create_sub((chunk["offset"], chunk["duration"]), chunk["text"])
                  return sub_maker

              sub_maker = asyncio.run(_do())
              if not sub_maker or not sub_maker.subs:
                  logger.warning(f"failed, sub_maker is None or sub_maker.subs is None")
                  continue

              logger.info(f"completed, output file: {voice_file}")
              return sub_maker
          except Exception as e:
              logger.error(f"failed, error: {str(e)}")
      return None

之前是能工作的，然后这两天就不行了。怀疑是：TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4 但是不知道这个是怎么来的。

xushijie commented 1 month ago

please upgrade edge_tts to 6.1.13.

9ihbd2DZSMjtsf7vecXjz commented 1 month ago

please upgrade edge_tts to 6.1.13.

请教要用什么方法升级,pip install edge-tts 这种方法升级完,还是合成语音403, 求指点

2024-10-20 00:41:00.203 | DEBUG | app.services.task:generate_terms:52 - video terms: [ "stargazing", "starry night", "stars and moon", "night sky", "astronomy" ]

2024-10-20 00:41:00.295 | INFO | app.services.task:generate_audio:75 -

generating audio

2024-10-20 00:41:00.299 | INFO | app.services.voice:azure_tts_v1:1057 - start, voice name: zh-CN-XiaoxiaoNeural, try: 1

2024-10-20 00:41:01.732 | ERROR | app.services.voice:azure_tts_v1:1080 - failed, error: 403, message='Invalid response status', url=URL('wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4&ConnectionId=0d725972364d4128a03afdb8a6332bb5')

2024-10-20 00:41:01.740 | INFO | app.services.voice:azure_tts_v1:1057 - start, voice name: zh-CN-XiaoxiaoNeural, try: 2

2024-10-20 00:41:03.368 | ERROR | app.services.voice:azure_tts_v1:1080 - failed, error: 403, message='Invalid response status', url=URL('wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4&ConnectionId=9ab51e6a30b64dcea81dbfce3ba233f1')

2024-10-20 00:41:03.377 | INFO | app.services.voice:azure_tts_v1:1057 - start, voice name: zh-CN-XiaoxiaoNeural, try: 3

2024-10-20 00:41:04.804 | ERROR | app.services.voice:azure_tts_v1:1080 - failed, error: 403, message='Invalid response status', url=URL('wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=6A5AA1D4EAFF4E9FB37E23D68491D6F4&ConnectionId=e79414d188c1457d84459b2eab4194c2')

2024-10-20 00:41:04.813 | ERROR | app.services.task:generate_audio:85 - failed to generate audio:

check if the language of the voice matches the language of the video script.
check if the network is available. If you are in China, it is recommended to use a VPN and enable the global traffic mode.

MewoTrix commented 1 month ago

please upgrade edge_tts to 6.1.13.

感谢提供思路，将edge_tts换到最新版之后软件开始工作了，但不知道为什么不自动调用本地全局设置的site-packages文件夹，而是用它自己软件目录下的，这就导致需要把更新好的库般进去软件目录下的site-packages文件夹XD

9ihbd2DZSMjtsf7vecXjz commented 1 month ago

please upgrade edge_tts to 6.1.13.

感谢提供思路，将edge_tts换到最新版之后软件开始工作了，但不知道为什么不自动调用本地全局设置的site-packages文件夹，而是用它自己软件目录下的，这就导致需要把更新好的库般进去软件目录下的site-packages文件夹XD

请问通过什么方法升级?

MewoTrix commented 1 month ago

please upgrade edge_tts to 6.1.13.

感谢提供思路，将edge_tts换到最新版之后软件开始工作了，但不知道为什么不自动调用本地全局设置的site-packages文件夹，而是用它自己软件目录下的，这就导致需要把更新好的库般进去软件目录下的site-packages文件夹XD

请问通过什么方法升级?

pip指令