Slang Labs, a startup based in Bengaluru and backed by Google, has launched CONVA. It is a full-stack solution that enables multilingual voice search capabilities within e-commerce apps. The platform is provided as an SDK and can be integrated into existing e-commerce apps in less than 30 minutes, without developers needing prior knowledge of advanced voice technology concepts like Automatic Speech Recognition (ASR), Natural Language Processing (NLP), and Text-to-Speech (TTS).
With CONVA-powered voice search, users can naturally speak in their own language while searching for products and information within e-commerce mobile and web apps. This feature allows the brand to maintain its app backend in English while enabling customers to search for products using their typical colloquial terms for well-known products using voice search.
For example, CONVA can understand mixed-code utterances, where people use English and another vernacular language in the same sentence while searching for something. Customers can conveniently search for products using their typical colloquial terms for well-known products using voice search that is enabled by CONVA, and the apps will still be able to recognize the correct product being searched.
CONVA is currently available for use in e-commerce, retail, travel, and trading apps. Its models have been trained on a wide range of SKUs from industries like groceries, FMCG, medicines, fashion, beauty products, cosmetics, and food names. Additionally, CONVA models are pre-trained on thousands of Indian place names, train stations, airport terminals, bus pickup and drop-off points inside cities and towns, as well as all the equities traded on the BSE and NSE exchanges.