Audio Transcription

The audio transcription feature uses AI technology to automatically recognize human voices in audio or video files uploaded by users, converting speech into text content, while also supporting SRT format subtitle extraction.

Use Cases

Through the audio transcription feature, you can quickly understand audio or video content in text form, and it can also be used for content creation. For example:

1. Record a voice memo, then use this feature to quickly generate a transcript. 2. Recording foreign language courses/meetings - if you can't keep up with the speech, you can record first and then use this feature to convert it to text. 3. Video subtitle creation - users can upload videos and then obtain SRT format subtitle files.

How to Use

Find the `Audio Transcription` menu in the TransDuck backend, enter this feature, and you can see the specific operation page:

Users only need to upload audio or video, then select the corresponding language, submit the task, and after waiting a moment, you can see the transcription results, like this:

If you need to get subtitles, you can directly click: SRT Subtitle Download.