We are an R&D company in speech and language technology, founded as a spin-off of LIMSI (now LISN), a French CNRS laboratory that has been conducting research in this field since the 1970s.

We provide solutions and expertise for core speech processing technologies such as speech recognition, language identification and speaker recognition. We have speech-to-text technologies for many languages including Arabic, Cantonese, Czech, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Hungarian, Italian, Latvian, Lithuanian, Mandarin, Persian, Pashto, Polish, Portuguese, Romanian, Russian, Spanish, Swahili, Swedish, Turkish, Ukrainian and Urdu, as well as some dialects of these languages and many under-resourced languages not listed here.

The VoxSigma software suite is the latest generation of speech processing software offered by Vocapia Research, making use of statistical models, such as neural networks, to build leading edge speech processing technologies for a number of use cases, such as broadcast monitoring, debate and conference call transcription, telephone speech analytics, voice interfaces, and VHF/UHF communication analysis.

Drawing from our research foundation, we are passionate about addressing complex use cases that involve challenging acoustic and linguistic conditions, often with limited computational and language resources. As a result, we actively participate in a range of collaborative, multiparty R&D projects, both at the national and international levels, and we are always open to new project opportunities. We can provide accurate tailored solutions that cannot be matched with general-purpose open-source solutions.

VoxSigma software is available both as a standalone software and as a Web service sharing the same functionalities.

To learn more about Vocapia Research use the contact information form.