Create transcription<br/> > Transcription template<br/>

The automatic transcription is created with the help of artificial intelligence (AI). Your audio data is transcoded on your device. Depending on the size of the language model, this requires large amounts of RAM (approx. 7 GB) and a lot of computing power.

You will find a selection of common transcription settings in the drop-down menu.

The transcription template specifies the settings with which the language is to be analyzed and the text generated. Select this from the drop-down menu.

There is a choice:

Do not transcribe
Load transcription from file
Blockwise transcription, not segmented
Blockwise transcription, segmented
Entire text, not segmented
Entire text, segmented
Word by word

The symbols on the templates (snail, pedestrian, bicycle, car, rocket) indicate how accurately and therefore how slowly or quickly the transcription is performed. When you move the mouse over the symbols, you will see detailed information on the specifications.

The division (entire text, blocks, words) determines how many timing marks are generated for the transcribed text. These markers have an influence on the fade-in options of the text.

Using the division Words, each word is given a time stamp and can therefore be displayed individually with a specific effect.

If you select Blocks, you will receive the text with a separation into longer phrases or sentences.

The selection of Entire text is recommended if you only want to export what is said in the source material as a simple text file.

The settings button to the right of the transcription template menu offers further setting options.

The calculation is carried out in the CPU.
PRO Bietet der Computer die technischen Voraussetzungen, kann die Transkription auch durch in der Grafikkarte erfolgen.

How long the transcription takes depends not only on the selected model settings but also on the performance of your hardware and the volume of text to be transcribed.

The source language is automatically recognized by default.
PRO Alternatively, specify the language in which your video or sound file is available. This can increase the accuracy of the transcription.

PRO If the text is to be automatically translated into English, activate the corresponding field.

It is only possible to save changed settings in the PRO-Version.

Examples of different transcription templates (with output template 1):

The transcription template Blocks, not segmented immediately displays one to several sentences and shows the next sentences when ready.

The transcription template Blocks, segmented fades in the spoken text word by word until one or two sentences can be seen together. Then the next words and sentences appear.

The transcription template Words segments everything, each word is displayed individually until the next word is spoken.

Load transcription from file

You can link existing subtitle timing files (e.g. *.ass or *.srt) to your sound or video via the transcription template selection Load transcription from file. This method is suitable if you already have such a file.

The Load transcription from file procedure can also be used if you first output a transcription for your source file as a subtitle file, edit incorrect passages in an editor and use the corrected file to create the final video. See also Editing the transcription