Main Interface Options and Their Meanings
As shown in the image above, the function of each option is as follows:
- Select Video: Select the original video to be translated. The video must contain human speech, and the audio must be clear without excessive noise. Otherwise, the recognition results will not be accurate. Please note that if there is no speech, it is not allowed, regardless of whether there are subtitles or not, because the principle of this software is to generate subtitles by recognizing human speech. You can hold down the ctrl key to select multiple videos at once, but the spoken language in all videos must be the same.
- Translation Channel: FreeGoogle and Microsoft can be used directly without proxy and configuration. Other translation channels are either free but require a proxy, such as Google, or require configuration, such as Baidu Translate and Tencent Translate. If you don't understand, it is recommended to choose Microsoft or FreeGoogle.
- Source Language: Select the spoken language of the human speech in the video. For example, if the human speech in the video is in English, then English must be selected here.
- Target Language: Select the target language to translate to. For example, if you want to translate the video into Chinese pronunciation and embed Chinese subtitles, then you need to select Simplified Chinese here.
- Network Proxy Address: If you use services such as Google or Gemini that are inaccessible in China, you must fill in the proxy address. For example, if you use a certain v2ray software, fill in http://127.0.0.12:1:10809. If you don't understand proxies, please do not fill in anything randomly, and do not use services that are inaccessible in China.
- Dubbing Channel: edgeTTS is free and requires no configuration, and can be used directly. Other dubbing channels require configuration or installation. If you don't understand, it is recommended to choose edgeTTS.
- Dubbing Role: Select the speaker role. Different roles have different voices. You need to select the target language first before selecting the role.
- faster Mode: The mode used to recognize human speech in the video. If you don't understand, choose the default faster mode.
- tiny: The model used to recognize human speech in the video. The default includes the tiny model under the faster mode. It is recommended to choose a medium or larger model for higher accuracy. If you choose faster mode and openai mode, you need to download the model to the models directory under the software directory. By default, only the tiny model under faster mode is included. Other model download addresses: https://github.com/jianchang512/stt/releases/tag/0.0 If you don't understand much and just want to try it simply, choose tiny here. No download is required for direct use.
- Overall Recognition: Default is fine. No need to change.
- Embed Subtitles: The way subtitles are embedded into the video. Soft subtitles require player support to be displayed and cannot be displayed on web pages. Hard subtitles are displayed wherever they are played, including web pages.
- Video End: The dubbing time may be longer than the original video time. Selecting this will extend the video by 10ms at the end until the dubbing is finished. It is recommended to select this.
- Automatic Dubbing Acceleration: The dubbing time may be longer than the original language time. Selecting this will force the speed to be increased to achieve consistency. The maximum acceleration can be modified in Menu -- Tools/Advanced Settings -- Advanced Settings.
- Automatic Video Slowdown: Selecting this will slow down the video to align the video and audio subtitles. The slowdown can also be controlled in the advanced settings menu.
- Retain Background Sound: Selecting this will retain the original background sounds in the video, such as background music. If you select this, the processing speed will be slower, especially for larger videos.
- CUDA Acceleration: If you have an NVIDIA card on Win and Linux machines, you can use it for acceleration. You need to install the CUDA environment on your machine. Installation instructions can be found at https://pyvideotrans.com/gpu.html
- Clean Generated Files: If you repeatedly execute the same video, you can select this to delete the already generated files and regenerate them.
- Shutdown After Completion: Whether to shut down the computer after the task is completed.
- Start Processing: After everything is ready, click to start execution.
- Import Subtitles: If you want to use existing local subtitles, you can click to import them. After importing, they will be used directly and recognition will not be performed.
- Overall Dubbing Speed: For example, 10 means the speed is increased by 10% based on the normal speed, -10 means decreased by 10%.
- Volume +: Increase or decrease the volume based on the normal volume. Only effective under edgeTTS.
- Pitch +: Increase or decrease the pitch based on the normal pitch. Only effective under edgeTTS.