More than "OCR for Voice"

We’ve been developing solutions for users of speech technology for almost a dozen years, so we know how to deliver the solutions that our customers need. Especially in demanding and noisy environments, pushing audio through a speech recogniser proves that Garbage In gives Garbage Out. Leverage our experience and our mistakes, and let us help you build a solution, rather than create more problems.

REST easy

Our API-first strategy means that you can easily integrate our capabilities directly into your solution, be it just converting audio to smart text, or using our advanced search, biometrics and NLP. We pioneered the use of GPU technology for commercial speech processing, which means we can help you scale to huge volumes in the smallest possible footprint.

GPUs are essentially large groups of small processors that can carry out many processing jobs at once, in parallel with the central processor. With current solutions, this parallel computing approach can transcribe up to 1,200 hours of audio per hour.

Totally Private

We love the cloud, but many customers want to control what happens to their, and their customers’ data. We don’t provide a cloud API: instead we let you deploy on-premise, in your data centre, or in your own private AWS or Azure environment, complete with on-demand auto-scaling. All the benefits of a cloud API, but none of the worries about where sensitive data ends up.

I'd like to teach the world..

IV is fully trainable to quickly understand how you and your customers speak. Our “QuickTrain” methodology lets you add context-specific language in a matter of minutes. And best of all, it is available in 24 languages and dialects. And using our “SmartTranscript” outputs, you can let your customers “see” their audio as well as listen to it.