Voice of India - Urdu: leaderboard

Speech recognition on the Urdu part of Voice of India (2026), a closed benchmark of unscripted telephone conversations in Indian languages, scored with an orthographically informed word error rate that accepts permissible spelling variants. Percent, can exceed 100; lower is better.

Metric: Orthographically informed word error rate (OIWER, %; can exceed 100) on the Urdu unscripted telephone-conversation utterances of the closed Voice of India benchmark, transcripts with lattices of permissible spelling variants; systems run at default inference settings and only where they support the language; lower is better. Source: arxiv.org. Saturation forecast: Around March 2028. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Sarvam Audio7
2IndicConformer8.1
3Gemini 3 Pro9.1#145
4Gemini 3 Flash11.9#175
5omniASR_LLM_7B16
6omniASR_LLM_1B17.2
7Microsoft Speech-to-Text25.2
8elevenlabs-scribe_v225.5
9AssemblyAI Universal31.9
10GPT-4o Transcribe35.4
11gpt-4o-mini-transcribe52

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=voice-of-india-urdu · How It Works · Data refreshed daily, snapshot 2026-11-21.