Support for video. We've added the ability to import a video and edit the audio. With synchronization between voiceovers or dialogue and the video content, the users can create custom voice-overs from scratches, or edit an existing voice-over, with more ease.
Tutorials. We've added a step-by-step tutorial feature with three introductory tutorials, covering basic aspects such as UI overview, how to perform Speech-To-Speech Morph and how to operate Speech-To-Text.
Custom Voice deletion. Custom Voices can be deleted and removed from the library.
Splitable Transcription Blocks. Transcription blocks can now be split.
Move Effect available in TimeLocked Mode. Audio can now be moved also when in TimeLocked Mode.
Focusable elements. In web we've enabled focus state on input components, allowing the user to switch between them directly with the keyboard.
Fix copy and paste not working on MacOS.
Fix block cutting in Video mode.
Fix sub context menu going out of bounds.
Fixes to TimeLocked mode.
Improve Rapid Custom Voice Creation user experience. The overall experience of rapid cloning is been improved, with better UI and guiding the user through the various steps.
Improve library filtering system. TTS Voices can now be filtered both by Language and Country.
Improve Spectrogram performance.
Improve API error log when compute server is not installed.
improve trim silences.