Article

Global AI Speech Recognition Models Fail Indian Languages, Impacting Critical Services

OECD AI Incidents Monitor · oecd.ai

The OECD's record of the Voice of India findings as a risk to welfare and health services.

Open on oecd.ai ↗

The question it answers

  1. Where does AI still get Indian languages wrong, and how do I check its answer?

Read with it

  1. Reports AI4Bharat and Josh Talks' Voice of India test of speech recognition across 15 languages and many dialects, with error... thehindubusinessline.com Article OpenAI, Meta speech models struggle with Indian languages The Hindu BusinessLine
  2. A real case of auto-translation reversing the meaning of a Kannada message, and the complaint that followed. inc42.com Article Karnataka CM Siddaramaiah Calls Out Meta For 'Faulty' Kannada Translation Inc42
  3. OpenAI's test of 2,278 questions on Indian culture in 12 languages including Hinglish, written by 261 Indian experts, and why... openai.com Article Introducing IndQA OpenAI
  4. A study of real health messages in five Indian languages and Nepali, finding models handle romanized text up to 24 points worse... arxiv.org Article Script Gap: Evaluating LLM Triage on Indian Languages in Native vs Romanized Scripts in a Real World Setting arXiv (research paper)
  5. A 2026 benchmark showing models follow instructions less well as messages mix more English into Indian languages written in... arxiv.org Article Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions arXiv (research paper)
  6. Video AI4Bharat at IIT Madras and Josh Talks AI Launches India's First Independent AI Evaluation Platform AIM Network
eChai Partner Brands The partnership →