Home / Archives / July 2026 / Articles

REAL-TIME MULTILINGUAL CONVERSATIONAL AI USING SPEECH RECOGNITION AND TEXT-TO-SPEECH

Authors: Kasukurthi Manisha, Dr. SSN. Anjaneyulu

Country: India

Abstract

Artificial Intelligence has revolutionized the way users interact with digital systems, making conversational applications more efficient and intelligent. This project introduces a multilingual conversational AI that enables communication through both text and voice. The system is designed to understand user queries in multiple languages and generate accurate, context-aware responses using a powerful language model. The application integrates a backend supported by a large language model API to process user requests. It supports multiple languages, including English, Telugu, Hindi, and others. The system also provides voice interaction by converting spoken input into text through speech recognition and generating spoken responses using text-tospeech technology. The user interface is developed using Streamlit, offering a simple, interactive, and user-friendly experience. By combining multilingual support with voice capabilities, the application improves accessibility and allows users to interact naturally using their preferred language and communication method.

Keywords

AI-Based Chat System, Cross-Language Communication, Voice Assistant, Language Intelligence, Speech Processing, Interactive Application, Human-Computer Interaction

References

[1] OpenAI, OpenAI API Documentation. Available: https://platform.openai.com/docs
[2] Meta AI, Llama: Open and Efficient Foundation Language Models. Available: https://ai.meta.com/llama/
[3] Groq, Groq API Documentation. Available: https://console.groq.com/docs
[4] Google Cloud, Speech-to-Text Documentation. Available: https://cloud.google.com/speech-to-text
[5] Google, gTTS (Google Text-to-Speech) Documentation. Available: https://gtts.readthedocs.io/
[6] Streamlit, Streamlit Documentation. Available: https://docs.streamlit.io
[7] Daniel Jurafsky and James H. Martin, Speech and Language Processing, 3rd Edition (Draft), Pearson
Education.
[8] Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016.
[9] Hugging Face, Transformers Documentation. Available: https://huggingface.co/docs/transformers
[10] Christopher D. Manning and Hinrich Schütze, Foundations of Statistical Natural Language Processing, MIT
Press, 1999.