Gnani.ai, a Bengaluru-based enterprise voice AI startup, released Prisma v2.5, a speech-to-text model supporting 12 languages, on June 17. The model was trained on 14 million hours of proprietary Indic speech data and is now available to enterprise customers via APIs. Prisma v2.5 is designed to transcribe Indian-language speech, accounting for dialect variation, background noise, and mid-sentence code-switching. Gnani.ai reports that it benchmarked Prisma on word and character error rates, with both internal and third-party evaluations indicating it outperforms ElevenLabs, Sarvam AI, and Microsoft on these metrics, though the company did not disclose its benchmark methodology or specific scores. The company attributes lower latency to hosting the model in Indian data centres, including E2E Networks’ infrastructure. The current release supports only Indian languages, with plans to expand to Japan, the Philippines, and the Middle East. Prisma v2.5 builds on Vachana STT, launched in December 2025, and Inya, introduced at the India Impact AI Summit 2026. Gnani.ai raised $10 million in a Series B round in March, led by Aavishkaar Capital with participation from InfoEdge Ventures.