One of the Wild Dolphin Project (WDPs) main goals is to analyze the way dolphins vocalize and how that can affect their social interactions. With decades of underwater recordings, researchers have managed to connect some basic activities to specific sounds. WDP researchers believe that understanding the structure and patterns of dolphin vocalizations is necessary to determine if their communication rises to the level of a language. The ultimate goal is to speak dolphin, if indeed there is such a language.
The pursuit of this goal has led WDP to create a massive, meticulously labeled data set, which Google says is perfect for analysis with generative AI. Google says it trained the model using the Wild Dolphin Project's acoustic archive. It's an audio-in, audio-out model. After providing it with a dolphin vocalization, the model does just what human-centric language models do, it predicts the next token. If it works anything like a standard LLM, those predicted tokens could be sounds that a dolphin would understand.
More information:
https://arstechnica.com/science/2025/04/google-created-a-new-ai-model-for-talking-to-dolphins/