Voice of India - Kannada: leaderboard
Speech recognition on the Kannada 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 Kannada 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. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Sarvam Audio | 16.3 | |
| 2 | Saarika 2.5 | 16.4 | |
| 3 | Amazon Transcribe | 18.6 | |
| 4 | elevenlabs-scribe_v2 | 19.2 | |
| 5 | Gemini 3 Pro | 19.9 | #145 |
| 6 | IndicConformer | 21.4 | |
| 7 | Gemini 3 Flash | 22.2 | #175 |
| 8 | omniASR_LLM_7B | 39.2 | |
| 9 | omniASR_LLM_1B | 45.7 | |
| 10 | Deepgram Nova 3 | 53.7 | |
| 11 | GPT-4o Transcribe | 84.2 | |
| 12 | AssemblyAI Universal | 89 | |
| 13 | gpt-4o-mini-transcribe | 97.5 |
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-kannada · How It Works · Data refreshed daily, snapshot 2026-11-21.