voice recognition and synthesis
for Indian languages
with our voice support
with our ChatBot Service
and synthesis for Indian languages
with our voice support
with our ChatBot Service
IndiaSpeaks Research Labs
We are a team of passionate researchers and engineers set out to make businesses accessible to common man through VoiceTech. We develop language technology tools for Indian languages enabling businesses reach out to their customers in local languages. Our products use proprietary voice recognition, text-to-speech and natural language processing tools. With over a decade-long experience in the field of speech processing, we founded IndiaSpeaks in 2021 and have covered a significant ground in fulfilling our goal to enrich lives of millions of end-consumers across India. We have served multiple businesses across verticals like Entertainment, EdTech, FinTech and call centres. There is still a long way to go and new milestones to achieve
The heart of our voice recognition system is an advanced neural network architecture trained on high end GPU servers with high quality speech data. The speech data for every language is carefully collected from thousands of users to capture nuanced modalities of each language and then it is carefully pruned in-house to guarantee high quality speech recognition output. We boast of high scalability, adaptability and reliability of our models for any business, environment and user type. Use our technologies to shop, send e-mails, bank, book appointments and do many more tasks in your own language without touching a keypad.
We use state-of-the-art neural networks in our text-to-speech (TTS) system to convert any text in any Indian language to speech in real time. Our TTS voice is pleasant to hear and has high naturalness which makes it ideal for any automated response system. Along with our voice recognition, this technology is designed to break all language barriers.
Natural Language Processing
Our framework for building name entity recognition, intent recognition and intent-process flow using state machines and advanced neural networks enables businesses to build chatbots according to their requirements. Our latest machine translation and transliteration modules enable users and businesses to interact with each other in their preferred language of choice.
Our integrated voice recognition, TTS and NLP models with attractive interfaces can help businesses reduce the overhead cost in handling customer services and complaints. A carefully designed pipeline of intelligent products works as a well oiled engine that automatically approaches customers, identifies the problem, provides a solution and/or raises appropriate tickets and all this with minimal human intervention.
Dr. Madhavaraj A
Cofounder & CTO
Sasidharan is a tech enthusiast with 6 years of experience in DevOps and handled multiple projects in banking sector. He analyzes business requirements, functional specifications and executes them without a glitch.
Dr. Ganesh Ghalme
Dr. Ganesh is an Assistant Professor at IIT Hyderabad. He completed his PhD from Indian institute of Science, Bangalore in 2020 in Game Theory and Machine Learning. He handles data processing and operations at IndiaSpeaks. Dr. Ganesh believes in technologies that bring transformational change in human interactions
Mr. Sasidharan A
Cofounder & CEO
Prof. N. Viswanadham
Prof. Viswanadham is an INSA Senior Scientist at the Department of CSA, IISc. He is a Fellow of IEEE, IAS, INAE and TWAS. He worked as a professor in premier institutions like IISc Bangalore, NUS Singapore, and ISB Hyderabad. His research interests are blockchain, logistics, global supply chain networks and manufacturing. He is the author of four textbooks and over two hundred articles in top tier journals and conferences. Prof. Viswanadham advises IndiaSpeaks team on business and strategy.
Lt. Col. Saurabh Sharma
Lt. Col. Saurabh Sharma shares a collective dream of making voice solutions accessible to all. At IndiaSpeaks, he advises the team on strategy planning and business. An IISc graduate himself, he has extensive experience in speech data processing.
Harish Srigiriraju is a Principal Engineer at Verizon. He has expertise in leveraging advanced analytics and machine learning to improve software products. He has led several cross-functional projects to draw insights on user behavior and develop new features with help of various analytics tools and models. He has prior experience in software programming and graduated from Kellogg School of Management with an MBA. Outside of work he has a keen interest in advising startups to help them scale.