For decades, the voice of artificial intelligence was a sterile, polite, and unmistakably neutral being. Think of the original Siri, the GPS lady who never got lost, or the automated phone tree that asked you to please hold. These were voices designed to be inoffensive, efficient, and utterly devoid of personality. They were the customer service representatives of the uncanny valley.
The "new" in "text to speech wiseguy voice new" refers to a generational leap in training data. Early TTS models were trained on audiobooks and news anchors—clean, boring data. The new models are trained on film dialogue, specifically the golden era of gangster cinema (1970s-1990s). By ingesting thousands of hours of dialogue from The Godfather , Goodfellas , Casino , The Sopranos , and The Irishman , the AI learns not just the words, but the musicality of menace. text to speech wiseguy voice new