this will be an overview of our new dubbing Studio where we will explore all of the features available in this tool to fine-tune and edit your dubs on this main dubbing screen you are presented with many different options to upload your content for the purpose of this tutorial we'll be uploading a YouTube video by pasting the URL here let's start by naming our video I'm also going to choose the source language and the target language let's see I think I want this one to be in German next we're going to scroll down and locate create
a dubbing Studio project dubbing Studio cannot be applied to existing dubs so it's important to ensure this box is checked before creating your dub the quota cost is based on the length of the file and you will see that number reflected here dubbing studio also gives you free quota to edit your Generations but we'll get to that in a moment you also have the option to create a watermark on your video which will reduce the amount of quota used by 50% next let's expand the advanced settings dropdown similar to a regular dub you can choose
the number of speakers the desired resolution and a specific section of that video that you wish to dub I know that in this video there are two speakers I could leave it on detect but I'm going to help the AI out a bit and change it to two finally with all our desired parameters set we're now ready to create our dubbing Studio project once finished you will see an edit button next to the dub click that to open up the studio this is your main Studio screen let's start by switching this at the bottom to
German the top portion of your screen is the transcription and translation and the bottom portion of your screen is the audio timeline you can click and drag this bar on the top of your timeline to either increase or decrease the size of it to navigate throughout your timeline you can use the playhead above your tracks feel free to rename your speakers to keep yourself organized each speaker is divided and separated by color the grade out tracks are the clips of audio from the original language you can click these three dots here to delete that track
entirely if you feel that it was created incorrectly by the AI you'll notice that the background music from our video has been separated for this video I would like to completely mute the background music to do so click on this audio clip to select it then drag the volume slider all the way down to mute it let's revisit the top portion of your screen dubbing Studio has broken up each phrase into many sections that we call speaker cards the left side shows the transcription and the right side shows the translation let's play through a bit
to see how this turned out and hm I think we can get a better translation out of speaker number two suppose I wanted to change a word that was transcribed incorrectly or regenerate a voice that spoke poorly I can simply edit the text translate it by pressing this arrow in the middle and then regenerate the audio now let's have a listen great I like that better now you may notice in the bottom left corner it says free characters remaining this is a free quota amount given to you based on the length of your dub and
can be used for all the changes or regenerations we want to make in our video this number is completely separate from your overall quota in your subscription plan hence why we call them free characters let's take a look at our tracks again as there's some important settings we can examine on each speaker track there is a small COG icon click on it and it will bring up the voice settings to change these simply drag to your desired settings and the entire track will be affected you will now notice the word stale among your audio clips
this means changes or settings were made to the texts that have not yet been regenerated click either the stale button on each clip or on the speaker cards themselves alternatively to generate multiple clips of stale audio at once you can simply press the generate stale audio button in addition to adjusting the track settings you can also choose a different voice Al together the available voices you see are the same voices that are saved in your voice lab I'm going to demonstrate how to use a different voice let's replace one of these speakers with the voice
David BS from our voice library now I'm going to press generate stale audio on the bottom right again to hear this new voice replacing speaker number two now let's have a listen that sounds great as a side note all of these features are also accessible on the bottom right hand corner of the page to access these simply turn off the inherit track settings slider remember any settings or changes made to the speaker voice the transcription or the translation will require you to regenerate that stale audio you also have the option to split or merge audio
clips this is useful if the AI has broken up the phrases in an undesired way to merge simply click the merge button which is located between two audio clips from the original language track which you can see here you'll notice that the speaker cards will also merge once this action is completed please note that all clips should be less than 25 seconds in length to split a clip simply move your playhead to a specific section on your timeline and you will see the option to split on the original language clip again you will see this
reflected on the speaker cards and we will need to regenerate the audio since splitting affects two clips I'm going to once again click generate stale audio you can also rightclick an audio clip to access a few more options the most interesting option here is probably that you can create a clone from a specific clip one helpful tip is to find a clip that you like where you feel the voice is good and then rightclick to create a clone from that clip you can then assign that clone to an entire track to achieve a consistent voice
throughout this is just one tip and may not work for all circumstances but it can work very well in some cases another trick is that if you ever feel like a speaker is talking too quickly or too slowly you can click and drag an audio clip and press stale to regenerate it to fit the new length of that clip this can produce a more natural speaking Cadence if you wish to shorten a clip without warping the audio select the trim tool here and drag the audio clip you'll see that below the background track we also
have a foreground track we can add a clip to this foreground track here which will preserve audio from the original track that we feel is still important to our video adding Clips to the foreground track is also helpful to preserve things like laughing crying or any other miscellaneous sound effects in your video I'm going to add a clip here at the end of the video by placing it on the foreground track then I'm going to use this trim button to shorten the translated audio clip so that they don't overlap great now we can see that
the last phrase of this video is spoken in the original language great but the best way to feel grateful for something is to be deprived of it for a while if you wish to add a additional languages simply click the plus icon on the bottom all right now that we're happy with all of our edits it's time to download our dub video to do this click the export button on the bottom right here you are given several download options so make sure your desired option is selected then click export once finished you can either view
or download as an mp4 file and there you have it you're now ready to fully utilize the dubbing Studio project to edit your dubs we can't wait to see where your creativity takes you