In addition to the core video and audio translation, pyVideoTrans also provides multiple independent powerful features.

Transcribe and Translate Subtitles

Supported video formats: mp4/mov/avi/mkv/webm/mpeg/ogg/mts/ts

Supported audio formats: wav/mp3/m4a/flac/aac

This function is essentially the first half of the video translation workflow. It transcribes and generates an SRT subtitle file from the audio/video, translates that subtitle file into the specified language, and then stops. If you only want to generate subtitles based on audio/video, you can choose this function.

Batch Speech to Subtitles

Supported video formats: mp4/mov/avi/mkv/webm/mpeg/ogg/mts/ts

Supported audio formats: wav/mp3/m4a/flac/aac

This is a functional panel dedicated to transcribing audio/video files into text or subtitles. Sometimes you might not want to translate the video, but merely want to batch generate subtitles based on the audio/video; this function is perfect for that.

Batch transcribe video or audio files into subtitles or TXT. Simply drag in files, set the source language (spoken language) and recognition model, and you are ready to start. Supports advanced features like Resegment, Denoise, and Speaker Diarization.

Batch Translate SRT Subtitles

Supported subtitle format: srt

If you already have SRT subtitle files, this feature can help you quickly translate them into other languages while keeping the timeline unchanged. It also supports various output formats such as Single Language Subtitle, Target Language on Top (Dual), and Target Language on Bottom (Dual).

Batch Dubbing for Subtitles/Text-to-Speech

Supported subtitle or text formats: srt/txt

If you have many subtitle files or txt files and want to create dubbing for them in batch, you can choose this function.

Batch synthesize your SRT files or plain text into dubbing files (such as WAV or MP3) using the selected TTS engine. Supports fine-tuning of speech rate, volume, and pitch.

Multi-Role Dubbing for Subtitles

Supported subtitle or text format: srt

Similar to the Batch Dubbing function, with the difference that this function allows you to specify a distinct speaker for each line of subtitles, enabling multi-role dubbing.

Merge Audio, Video, and Subtitles

This is a practical post-production tool. When you have separate Video, Dubbing, and Subtitle files, you can use this to perfectly merge the three into a final video file, with support for custom subtitle styling.

Clip Video by Subtitles

If you have a video and a corresponding subtitle file (srt/ass/vtt) and want to clip out high-energy segments corresponding to specific subtitles, this function is suitable.

Select the video to be clipped and the corresponding subtitles, then select the specific subtitle segments you want to clip out. Options include: clip with sound (default), clip silent video only, clip audio only, or separate silent video and audio independently.

Real-time Speech to Text

Can listen to speech from the microphone and convert it to text in real-time, with a latency of less than 2 seconds. It can automatically segment recognized text, add punctuation, export to TXT, save recording files, etc.

Batch Merge Video and Audio

If you have many videos and many corresponding audio files and wish to embed the audio into the videos one by one, doing it manually would be troublesome and inefficient. Use this function to batch embed audio into videos.

Instructions

1. Create a folder and move the videos and audio files to be merged into it.

2. The video and audio files to be merged must have the same name (excluding the extension). The program uses this to determine which audio to embed into which video.

Assume the full video name is 001.mp4; the name without the extension is 001. Therefore, the audio file to be embedded into this video must have the name 001. If the audio is in WAV format, the full name will be 001.wav; if MP3, 001.mp3.

During processing, after getting 001.mp4, the software removes the suffix to get 001 and looks for 001.wav/001.mp3/001.flac/001.aac/001.m4a in the folder. If found, it embeds that audio into 001.mp4.

3. Select this folder in the software interface.

4. Set whether to keep the original sound in the video. If selected, the processed video will contain two audio tracks simultaneously: the original sound from the video file and the sound from the audio file.

Audio/Video Format Conversion

Used to batch convert audio or video to other formats, such as converting WAV audio to MP3.

Batch Merge Video and SRT Subtitles

Similar to batch video and audio merging, this allows you to embed subtitles into corresponding videos one by one. For example, if you have 20 videos and each has a corresponding SRT subtitle file, you can use this function to embed the 20 SRTs into the 20 videos at once.

Instructions

1. Create a folder and move the videos and SRT subtitle files to be merged into it.

2. The names of the video and subtitle files to be merged must be the same (excluding the extension). The program uses this to determine which SRT subtitle to embed into which video.

Assume the full video name is 001.mp4; the name without the extension is 001. Therefore, the SRT subtitle file to be embedded into this video must be named 001.srt.

During processing, after getting 001.mp4, the software removes the suffix to get 001 and looks for 001.srt in the folder. If found, it embeds that subtitle file into 001.mp4.

3. Select this folder in the software interface.

4. Defaults to embedding as hard subtitles. If "Embed Soft Subtitles" is selected, they will be embedded as soft subtitles. When using soft subtitles, you need to select the subtitle language, otherwise, characters may appear garbled. Also, note that soft subtitles require video player support; some domestic players may not display them or may show garbled characters.

Subtitle Format Conversion

Used to batch convert subtitle files from one format to another, such as converting SRT subtitles to ASS or VTT subtitles. Supports batch conversion.

Audio/Video Format Conversion

Used to batch convert audio or video to other formats, such as converting WAV audio to MP3.

Batch Extract Audio from Video

If you have a large number of videos and wish to extract the sound from them as audio files, you can use this function.

Instructions

1. Select video files in the software interface; you can select one or multiple.

2. Click to start execution. Once finished, click "Open Result Directory".

Separate Vocals and Background Music

The software comes with a simple vocal and background music separation tool. For smaller videos, you can use this tool to separate human speech and background sound into two files.

Click Menu -- Tools/Options -- Vocal/BGM Separation to open the interface shown below.

Click "Select Audio/Video File" to choose the file you want to separate, then click the Start Separation button. Note that the separation process is slow and time-consuming. If your video is large, consider using a dedicated vocal separation tool. For specific tutorials, see Vocal and Background Separation Tool.

Batch Add Image Watermark to Video

Open Menu -- Tools -- Add Watermark to Video, as shown below:

1. Select the video files to add watermarks to; one or multiple.
2. Select the watermark image.
3. Select watermark position: Top Left, Top Right, Bottom Right, Bottom Left, Center.
4. Set the margin distance from the top/bottom and sides. Default is 10 pixels.
5. Set the watermark size. It is recommended to process the image dimensions in advance and set this size to the actual image size to prevent distortion. Default is 50x50 (width 50px, height 50px).
6. Click to start execution. Wait for completion, then open the result save directory to see the result files.