As artificial intelligence enters every aspect of life, it does not escape the attention of social media platforms. In this context, TikTok continues to offer important innovations. Finally, it was revealed that TikTok has developed a voice cloning tool for users.
TikTok is developing a voice cloning tool
TikTok is working on a feature that synthesizes speech from text using user voices. The AI-powered voice cloning tool will allow to copy the user’s voice in as little as 10 seconds.
The tests conducted by TikTok revealed the feature called “TikTok Voice Library”. With this feature, users will be able to create a digital copy of their voice by recording a short sample. TikTok needs only 10 seconds of speech for the voice clone to be produced by artificial intelligence.
Once a user’s audio profile has been created and saved in the Sound Library, they will be able to add those sounds to their videos. So with just a 10-second audio sample, you will be able to include your own voice in all videos. The cloned audio will be unique to the user and will only be available on the user’s own account.
The feature seen in the application code is still in its early stages. However, it will involve a registration process where users agree to terms and conditions. However, the ability to store text samples seems to be yet to be developed.
If TikTok’s voice cloning tool is rolled out, it could pave the way for new video styles on the platform. But it also raises privacy questions about how audio data is stored and what it will ask of users.
{{user}} {{datetime}}
{{text}}