Gnani AI Launches Prisma v3.0 Speech Recognition Model for 10 Languages
Prisma v3.0 is designed to handle code-mixed conversations where speakers switch between Indian languages and English. The model outperforms competitors like Microsoft Azure and Deepgram on the Vistaar benchmark and offers four distinct transcription modes. It also allows developers to use custom vocabulary prompting for technical terms and brand names.
Key points
- Supports 10 languages including Hindi, Bengali, and Tamil
- Features four modes: Verbatim, Transcribe, Code-mix, and Transliterate
- Outperforms ElevenLabs and Microsoft Azure on Vistaar benchmark
- Supports custom vocabulary prompting for up to 200 terms
Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. Analytics India Magazine did the reporting; read the original for the full story.
Read the full story at Analytics India Magazine
