Tenstorrent and Smallest.ai Partner to Bring Production-Grade Voice AI On-Prem

Tenstorrent and Smallest.ai have partnered to deliver an on-prem voice AI stack that runs Smallest.ai's Lightning V2 real-time text-to-speech model natively on Tenstorrent Galaxy Blackhole servers, aiming to reduce deployment costs while meeting real-time performance needs. Smallest.ai said working with Tenstorrent's NoC and larger SRAM unlocked 4x gains at a fraction of the cost of comparable GPU infrastructure, and the joint solution targets high-volume, data-sensitive use cases in financial services, telecom, healthcare, and enterprise. Lightning V2 is available on Tenstorrent hardware today with usage-based pricing and no upfront commitments.