What is Sieve?

It typically takes months to setup everything you need to build, experiment with, and deploy AI applications on video and audio data.

Sieve is a tool that makes it easy to build and deploy video and audio AI applications, with your entire team. Some features include:

  • Pre-built, production-ready apps and models your can use in a single click or API call
  • Build complex apps that use many models in a few lines of code
  • Instant no-code interfaces for every app on Sieve, with zero extra configuration
  • Shareable links to every job request sent to Sieve
  • Attaching compute resources to functions in a single line of code (CPU, GPU, system packages, python packages, etc)
  • Reliable, horizontally scaling infrastructure based on traffic
  • Powerful distributed primitives like queues and function-in-function calling to parallelize data processing
  • Streaming output support


All you need to get started with Sieve is an account which you can sign up for here. From there, you can decide what you’d like to do next.

How it Works

At its core Sieve is an ML runtime focused on ease-of-use and collaboration. Users can deploy completely custom functions on arbitrary hardware and get access to primitives that make it easy to build increasingly complex applications. On top of the runtime, Sieve offers many production-ready solutions of its own that solve use cases out-of-the-box. The benefit of this is that you don’t need to think about infrastructure, or even which models to deploy if you don’t want to — just the higher level logic of integrating various models into your application.


If you need any assistance or have any questions, you can reach out to our support team through our website or by joining our community Slack channel. We are available to help you with any issues or concerns you may have and ensure that your experience with Sieve is smooth and successful.