#8657 gemini-3.8-flash is currently experiencing high demand, spikes in demand are usually temporary. Please try again later.T

118.69**2 Posted at: 2 hours ago

gemini-3.8-flash is currently experiencing high demand, spikes in demand are usually temporary. Please try again later.
Traceback (most recent call last):
File "google\genai\_gaos\interactions.py", line 756, in create

return _speakeasy_parse_response(http_res)

File "google\genai\_gaos\interactions.py", line 504, in _speakeasy_parse_response

raise errors.CreateInteractionServerError(

google.genai._gaos.errors.createinteraction.CreateInteractionServerError: gemini-3.8-flash is currently experiencing high demand, spikes in demand are usually temporary. Please try again later.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "videotrans\task\only_one.py", line 90, in run
File "videotrans\task\_stage_translate.py", line 31, in trans
File "videotrans\translator\_runner.py", line 71, in run
File "videotrans\translator\_base.py", line 85, in run
File "tenacity\__init__.py", line 480, in call
File "videotrans\translator\_gemini.py", line 47, in _item_task
File "google\genai\_gaos\google_genai.py", line 278, in create

response = wrap_sdk_call(

File "google\genai\_gaos\lib\compat_errors.py", line 368, in wrap_sdk_call

return fn(*args, **kwargs)

File "google\genai\_gaos\interactions.py", line 758, in create

response_helpers.raise_parse_error(

File "google\genai\_gaos\utils\response_helpers.py", line 92, in raise_parse_error

raise parse_error from exc

google.genai._gaos.lib.compat_errors.InternalServerError: Error code: 503 - {'error': {'message': 'gemini-3.8-flash is currently experiencing high demand, spikes in demand are usually temporary. Please try again later.', 'code': 'service_unavailable'}}

trk=[TransCreate]: uuid='0fd01847b4', proxy_str=None, cfg=[TaskCfgVTT]当前工作模式: 翻译视频 单视频模式
原始输入文件名: C:/Users/Admin/Downloads/vd 1.mp4,
输出结果保存到文件夹: C:/Users/Admin/Downloads/_video_out/vd 1-mp4,
临时文件夹: C:/Users/Admin/Desktop/Pyvideo/tmp/1836/0fd01847b4
已选 清理已存在
已启用CUDA加速
STT Service:faster-whisper(Built-in), large-v3-turbo, 发音语言: Simplified Chinese, , 数据类型:default
TranslateSrt:Gemini AI,原始语言:Simplified Chinese,目标语言:Vietnamese, 已选 SendSRT, settings.get('trans_thread')=5, settings.get('aitrans_thread')=40
TTS Service:Edge-TTS (Free), 角色:NamMinh(Male/VN), 配音语言:Vietnamese
音量:+10%, 语速:+12%, 已选 音频加速, 未选 视频慢速
已选 移除每条字幕配音开头和结尾静音缓冲
静音移除力度: default
字幕: Hard Subtitles , precent=12, hasend=False, should_recogn=True, should_trans=True, should_dubbing=True, should_hebing=True, is_copy_video=True, video_codec_num=264, ignore_align=False, is_audio_trans=False, clone_ref='', should_recogn2=False, do_diarize=True
video_duration_ms=209633


=
system:Windows-10-10.0.26200-SP0
version:v4.17
frozen:True
language:en_US
root_dir:C:/Users/Admin/Desktop/Pyvideo

1 Replies

#1 DeepSeek reply at 2 hours ago

This is not a software bug: the Gemini API returned HTTP 503 service_unavailable, which means the model gemini-3.8-flash is temporarily overloaded on the server side.

Solutions:

  1. Wait a while (usually from a few minutes to a few hours), then start the task again. Because Clear Output is checked, the transcription stage has to be redone, but the previously generated subtitles will not be reused. You can uncheck it only when it does not conflict with the current input; if you want to keep the recognized subtitles, you can also use single-video mode to import the already-recognized srt subtitles.
  2. Reduce concurrency: in Menu → Tools/Options → Advanced Options → Subtitle Translation, lower AI Translation Batch Size (Lines) (the log shows aitrans_thread=40, which is too high and makes it easy to hit Gemini's rate limits). Set it to 10–20 first, or even 1.
  3. Increase the retry count: in Advanced Options → General Settings → Retry Attempts on Failure, set it to 3–5, so that temporary 503 responses are retried automatically.
  4. Switch to another translation channel: Gemini's free tier is heavily rate-limited. Change to DeepSeek (low cost, full AI quality) or Zhipu AI / OpenAI ChatGPT; the configuration entry for each channel is in Menu → Translation Settings.
  5. If you must use Gemini, switch to another model in the Gemini settings window, or fill in an API key with a higher quota.

Please refer to the related documentation:

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Dondate via ko-fi.com

Related resource