Block’s new voice model sounds eerily human
techcrunch.comIvan Mehta
Block has released a voice model capable of running locally on MacBook M4 Max hardware, producing speech output that closely mimics human characteristics. The on-device capability indicates practical accessibility for desktop users without relying on external services.
Why it mattersLocal voice generation on consumer hardware means AI tools readers can experiment with realistic speech synthesis without API costs or latency concerns, enabling new applications in podcasting, voiceovers, and accessibility tools.
From the source: Block said that the voice model can run locally on a MacBook M4 MaxRead at techcrunch.com