Voice of India - Odia: leaderboard

Speech recognition on the Odia 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 Odia 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 Audio14
2IndicConformer14.4
3Saarika 2.515.1
4Amazon Transcribe17.9
5elevenlabs-scribe_v220.7
6Gemini 3 Pro20.9#145
7Gemini 3 Flash26.1#175
8gpt-4o-mini-transcribe42.1
9GPT-4o Transcribe72.5
10omniASR_LLM_7B72.6
11omniASR_LLM_1B89.8

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-odia · How It Works · Data refreshed daily, snapshot 2026-11-21.