the CIIL translation tool that integrates transliteration and language models. You can translate text of any Indian language (including English) to any Indian language (including English). This web application also supports transliteration of both source and target text. For ease of access, we have also implemented language detection module to identify the language of the source text automatically. However, users can still choose the language they want to translate from.

A transliteration application that converts text from one script to another script. For this purpose, we use a unicode character mapping mechanism. This works well for all the Indian languages using Brahmi based scripts (which covers all Indian languages except for Urdu and Kashmiri in Arabic script).

the web based OCR tool developed by LDC-IL integrates varios OCR models developed by different organizations and individuals as part of their research and they have all been pulled together to work on a single platform as available on this tool. On the base, we use the Tesseract, bare-bones OCR engine which is an open-source OCR engine. We build a wrapper on top of it to make it a web application and also an API that can be used in any web application and takes input as .PNG or .JPEG image as input. Users also need to select the language/script the image is in. It can also identify multiple languages if the text on the image is in multiple languages.

A transcription tool based on an ASR (Automatic Speech Recognition) system as developed using various sources. We also develop our own ASR tools and deploy them here. Users can get any audio file transcribed. They can speak to the system and get the text typed. They can also upload any audio file (preferably in .mp3 or .wav file) and get a transcript of the same as output

A text to speech tool. It is sourced with the available models and hosted here. This tool can speak any text given to it. It supports only a few language at present. We are still building more voices and sourcing other works already done. We will keep on updating it as we add more languages.