Guest
Presenting a refreshing new update to Synthesizer V Studio—version . Because this is a major update, we are releasing this first as a beta (). Feature 1 This new update utilizes Reinforcement Learning from Human Feedback (RLHF), a method previously employed in text generation AIs to steer the system towards generating more preferred responses. With this technology, which we are the first to apply to audio, we can “instruct“ the Synthesizer V AI to generate pitch curves that users find appealing. This translates to fewer off-key errors, better use of vibratos, and more expressive transitions between notes. Feature 2 We are enabling feedback submission for all users, to improve pitch generation and extend RLHF to the modeling of voice timbre. Within the AI Retakes panel, the heart icon on each take now also serves as a button for users to share their preferred takes with Dreamtonics. Models trained with this feedback data will be deployed in future voice database upda
