akashvani : now gets you live cricket scores in Indian languages

2026-02-14 · Source: Naturallanguageprocessing on Medium · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Data Science & Analytics · Depth: Fundamental Awareness, quick

Summary

Akashvani is an Android application and web service designed to provide live cricket scores spoken in 12 Indian languages, including Hindi, Tamil, Telugu, Bengali, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia, Urdu, and English. Developed by CX Data & Analytics LLC, the platform aims to simplify access to cricket updates for all users, particularly seniors, by offering a voice-first interface, large buttons, and no registration requirement. It supports scores from various series like IPL, T20, and Test matches, leveraging technologies such as GPT-3.5-turbo, Streamlit, OpenAI, gTTS, NewsAPI, GNews, SerpAPI, and PostgreSQL for its functionality. Users can access it via the Android app or akashvani.cxloop.co.

Key takeaway

For product designers targeting diverse demographics, particularly seniors, Akashvani demonstrates the value of voice-first, multilingual interfaces. You should consider integrating spoken output and simplified navigation to enhance accessibility and user engagement, especially for information-rich applications where reading small text can be a barrier.

Key insights

Akashvani delivers live cricket scores audibly in 12 Indian languages, prioritizing accessibility for seniors.

Principles

• Accessibility enhances user experience.
• Voice-first interfaces simplify information access.

Method

Users select a language, search for scores (e.g., "T20 score"), and the app speaks the live results. No registration is required.

In practice

• Offer voice output for diverse content.
• Design interfaces with large, clear controls.
• Support multiple native languages.

Topics

• Multilingual Audio
• Natural Language Processing
• Accessibility Features
• Live Sports Data
• API Integration

Best for: General Interest, Product Designer

Related on AIssential

• Voice of India: A Large-Scale Benchmark for Real-World Speech Recognition in India — Real-world Indic ASR requires benchmarks with unscripted speech, diverse languages, and flexible spelling.
• Google's Gemini 3.5 Live Translate delivers real-time voice translation across 70+ languages — Google's Gemini 3.5 Live Translate offers real-time, natural-sounding voice translation across 70+ languages, available via API and apps.
• Voice AI in India is hard — Wispr Flow is betting on it anyway — Adapting voice AI for linguistically diverse markets like India requires localized language models and aggressive pricing strategies.
• Live demo of AssemblyAI's Universal-3.5 Pro Realtime Speech-to-Text model — Contextual prompting and noise suppression significantly enhance real-time speech-to-text accuracy across diverse languages and challenging audio environments.
• A Multilingual Voice Analytics Module for Contact-Center Hiring — SR-Voice enhances contact-center hiring by analyzing vocal performance across emotion, communication, and rhythm dimensions.
• Granite 4.0 1B Speech: Compact, Multilingual, and Built for the Edge — Granite 4.0 1B Speech offers high accuracy and multilingual support in a compact, efficient model for edge devices.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Naturallanguageprocessing on Medium.