Voice Separation FAQ
- Audio Separation
Subscribe
🤔 Check out any questions you have regarding voice separation in advance!
Q. This is a feature I've never seen before. How do I use it?
•
It is very simple! When you upload an audio or video file, the audio tracks are automatically separated, allowing you to select and download files separated by speaker, reaction/sound effects, background music, and more.
Q. When would it be good to use this?
•
It is useful when you want to extract only the voice of a specific speaker from a file where multiple people are talking.
•
It can also be used when you want to extract only the background music, excluding the speaker's voice.
•
If you need only the remaining voices excluding a specific speaker, you can select the desired voice tracks and synthesize them into a single file for download without the need for a separate program.
Q. How is usage deducted?
•
Credits are deducted at a rate of 1x per second of file length . (e.g., Uploading a 3-minute 30-second file deducts 210 credits)
Q. When is the usage charged?
•
It is automatically charged on the Paymentth of every month .
Q. Is there a separate usage limit for each function?
•
No. You can freely use the features you want, such as dubbing, lip-dubbing, audio-to-video text conversion, and voice separation, within your monthly usage limit.
Q. How many languages are supported?
•
Over 99 languages of uploaded files are automatically detected .
Q. What files can I download?
File downloads are not supported on the Free plan.
•
Background audio
◦
Background Music : [Original Audio] - [Speaker Voice] - [Version with character sound effects (laughter, crying, applause, cheering, sighing, etc.) removed as much as possible]
◦
Background music with reactions : [Original voice] - [Speaker voice] + [Version with character sound effects]
◦
However, due to the nature of AI, 100% accuracy is not guaranteed.
•
Audio by Speaker
◦
Full speaker voice file
◦
Individual voice files by speaker
Q. Can I preview the separated audio or combine and export only the tracks I want?
•
Yes, it is possible! Audio tracks are provided as buttons at the top left of the results page, and you can preview them by selecting the desired track and clicking 'Play Audio'.
•
If you press the 'Export Voice' button, you can combine the selected tracks and download them as a single voice file .
Q. Is it possible to change the speaker?
•
Yes, it is possible. If you change the speaker of a specific script on the results page and download it, the script will be moved to the voice track of the changed speaker. When downloading after the update, you will receive an audio file that reflects the speaker change.
(*The update process may take some time.)
(*The update process may take some time.)
Subscribe to 'Perso AI Community Hub'
By subscribing to the site, you will be the first to receive the latest updates, including new posts, via notifications and email.
Subscribe to the Perso AI Community Hub!
Subscribe to the Perso AI Community Hub!
Subscribe