# Tenstorrent and Smallest.ai launch on-prem voice AI stack with 4x cost savings

Digest AI · Hardware & Compute · published 2026-10-01T17:09:01Z

Canonical: https://digestai.news/story/tenstorrent-and-smallest-ai-launch-on-prem-voice-ai-stack-with-4x-cost

## Summary

Tenstorrent and Smallest.ai announced a partnership on October 1, 2026, to deliver an on-premises voice AI stack combining Smallest.ai’s Lightning V2 real-time text-to-speech model with Tenstorrent’s Galaxy Blackhole servers. The joint solution aims to reduce deployment costs by up to 4x while maintaining real-time performance, targeting industries like financial services, healthcare, and telecom that prioritize data sovereignty and high-volume workloads.

The partnership leverages Tenstorrent’s Block FP8 compute architecture, which the companies claim achieves 23 PFLOPS with 6.2 GB of on-chip SRAM and 1 TB of GDDR6 memory. Smallest.ai’s research paper, published in April 2026, reports that Lightning V2 runs at LoFi fidelity and BlockFloat8 precision with minimal audio quality degradation. The paper also highlights a 3-4x reduction in upfront costs compared to NVIDIA L40S GPUs for similar workloads, citing a modeled scenario of 550 concurrent five-second TTS requests. Tenstorrent’s Galaxy Blackhole servers list for $160,000 each, with usage-based pricing and no upfront commitments.

## Key points

- Tenstorrent and Smallest.ai partner to offer on-prem voice AI stack with Lightning V2 on Galaxy Blackhole servers
- Lightning V2 achieves 4x lower cost than NVIDIA L40S while maintaining 95% LoFi computational fidelity and 80% BlockFloat8 deployment
- Galaxy Blackhole servers deliver 23 PFLOPS with 6.2 GB on-chip SRAM and 1 TB GDDR6 memory, priced at $160,000 each

## Why it matters

This partnership enables organizations to deploy high-performance, real-time voice agents on-premises at a fraction of the cost of traditional GPU solutions, addressing data sovereignty concerns in sensitive industries like finance and healthcare.

## Sources

1. [On-Prem Voice Agents Get New Hardware Path as Smallest.ai Joins Tenstorrent](https://unite.ai/on-prem-voice-agents-get-new-hardware-path-as-smallest-ai-joins-tenstorrent) (Unite.AI, 2026-10-01)

## Cite

Digest AI, "Tenstorrent and Smallest.ai launch on-prem voice AI stack with 4x cost savings", 1 October 2026, https://digestai.news/story/tenstorrent-and-smallest-ai-launch-on-prem-voice-ai-stack-with-4x-cost

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/tenstorrent-and-smallest-ai-launch-on-prem-voice-ai-stack-with-4x-cost.json