Fast inference for voice.

Our customers use Hopper today for two things:

  • GPT-4.1toGemma-4
  • ElevenLabstoQwen3-TTS
Talk to an Engineer
Hopper Inference circuit board

Meet the team

We’re Pavan and Jashwanth. Pavan ran voice inference at Salient, powering millions of calls a day. Jashwanth wrote inference kernels for Quest 3 at Meta Reality Labs.

We met in high school more than 13 years ago and studied together at IIT Madras.

  • Meta
  • ACM ICPC
  • Uber
  • Microsoft
  • Samsung
  • IIT Madras

We’re backed by Y Combinator and leaders including Vijay Krishnan (CTO of Turing), as well as others from xAI, Stripe, and Rubrik.

Writing