Reported about 8 hours ago
Nvidia has introduced Fugatto, a pioneering AI model capable of creating sound effects, mimicking voices, and composing music from natural language prompts. This innovative audio synthesis tool merges multiple functionalities, allowing it to perform tasks traditionally handled by separate models, like voice modulation and sound effect addition. Though still in its research phase and not yet planned for commercial release, Fugatto holds significant potential for industries such as entertainment and translation, while also raising discussions on its implications for artists and sound professionals.
Source: YAHOO