AIMediaNamaabout 5 hours ago
Gnani.ai launches Prisma v2.5 speech model
4 min read
Gnani.ai released Prisma v2.5, a speech-to-text model supporting 12 Indian languages, trained on 14 million hours of proprietary Indic speech data. The company claims it outperforms Sarvam AI, ElevenLabs, and Microsoft on word and character error rates. The model is available to enterprise customers via APIs.
Level
Hype check
Tap to vote and see what everyone thinks.
