pyVideoTrans

Appearance

v3.83 Version Update Notes ​

1. Enhanced Single Video Translation Capability ​

When only one video is selected, a separate subtitle editing window will pop up after the speech transcription is completed. You can modify the subtitles here to ensure greater accuracy in subsequent processes.

Subtitle editing window pops up after the speech recognition stage is completed

In the window that pops up after subtitle translation is completed, you can also assign a specific voice role to each subtitle line. If your chosen speech recognition service supports speaker diarization, you can set different voice roles for each speaker.

Subtitle editing and voice role modification window pops up after the subtitle translation stage is completed

Currently supported speech recognition services with speaker diarization are:

2. Added Doubao TTS Large Model 2.0 to Voice Synthesis Services ​

View details for the stable Doubao TTS Model 2.0

3. Added ByteDance Speech Recognition Large Model Fast Edition API to Speech Recognition Services ​

View details for ByteDance Speech Recognition Large Model Fast Edition

4. Enhanced Hard Subtitle Style Modification and Preview Function ​

Soft subtitle styles are controlled by the player and cannot be adjusted. Hard subtitle styles can be modified and adjusted before being embedded into the video. Click Hard Subtitle Style Adjustment on the main interface to open the modification and preview window.

5. Added Clip Video by Subtitles Feature ​

If you want to cut video clips based on corresponding subtitles, you can use this feature.

6. Other Optimizations ​

  • Optimized video slow-motion algorithm, improving time accuracy.
  • Added a confirmation dialog when Clean Generated Files is selected and files exist in the output directory.
  • Optimized UI layout, rearranged according to the Speech Recognition -> Subtitle Translation -> Voice Synthesis workflow.
  • Modified the order of items in the dropdown menus for Speech Recognition, Translation, and Voice Synthesis services.
  • Optimized the method for obtaining ffmpeg hardware encoding; it is now tested only once upon first use, unless the cache file videotrans/codec.json is deleted.
  • Added the -threads 0 parameter during ffmpeg processing to enhance multi-core support.