#4181 Connection timeout, please check network stability

This error indicates a network connection timeout, typically occurring when the software attempts to download AI models (e.g., for faster-whisper or Qwen-ASR) from huggingface.co or other online services, but the network is unstable or blocked.

Solution Steps:

1. Configure Network Proxy (if you have one): If you have access to a VPN or proxy service, enter its address (e.g., http://127.0.0.1:10808) in the "Network Proxy Address" field on the main interface. Leave it blank if you do not have one.

2. Manually Download the Model (Recommended for faster-whisper): Since automatic downloads from HuggingFace often fail, manually download the required model.

   • Step 1: In your software directory D:/py vt, navigate to the models folder.
   • Step 2: Create a new folder named exactly models--Systran--faster-whisper-large-v3 (if you intend to use the large-v3 model).
   • Step 3: Visit the model page: https://huggingface.co/Systran/faster-whisper-large-v3/tree/main. Download all .json, .bin, and .txt files from that page.
   • Step 4: Copy all downloaded files into the models--Systran--faster-whisper-large-v3 folder you created.
3. Check File Path: Ensure your software path D:/py vt does not contain spaces or special characters. It is recommended to rename the folder to D:/pyvideotrans to avoid potential issues.
4. Retry: After completing the manual download, restart the software and try the task again.

Please refer to the relevant documentation:

• Online Download AI Model Failure Solution
• Manual Download of Models for faster-whisper(local) Speech Recognition Channel

any solution, custom tts taking time for long videos and py translator cant able to wait for that. there no option to increase timeout limit

The core issue is that the software's default timeout for external API calls (like custom TTS) is insufficient for long videos, and there is no built-in setting to increase this timeout limit.

Solution Steps:

1. Understand the Limitation: The timeout is hardcoded within the software's network request logic for external services. There is no user-facing option in the GUI or advanced settings to modify this value.

2. Optimize TTS Service Performance: Since you cannot change the client-side timeout, you must reduce the processing time on the server side.

   • For Local TTS Services (F5-TTS, CosyVoice, etc.): Ensure your TTS service is running on a machine with sufficient GPU resources (CUDA). Check the service's logs for performance bottlenecks.
   • Reduce Request Batch Size: In Menu -> Tools/Options -> Advanced Options -> [Subtitle Dubbing Adjustment], try reducing the value of Concurrent Dubbing Threads to 1. This may prevent overloading the TTS service and reduce per-request latency.
   • Increase Pause Between Requests: In the same menu, increase Pause seconds after dubbing to a higher value (e.g., 10 seconds) to give the TTS service more breathing room between requests.

3. Alternative Workflow for Very Long Videos: Process the video in smaller segments.

   • Use video editing software to split your long video into shorter parts (e.g., 10-minute segments).
   • Process each segment separately in pyVideoTrans.
   • Use the software's "Batch merge video and audio" tool to recombine the finished segments.
4. Consider Different TTS Channels: If the custom TTS service is consistently slow, consider switching to a more robust TTS channel for long-form content, such as Edge-TTS (free) or a commercial API like Azure TTS or Qwen-TTS (Bailian), which typically have higher reliability and better throughput.

Please refer to the relevant documentation:

• AI Dubbing Error Analysis
• F5-TTS API Common Errors