Skip to navigation

saaras:v4 is now the default Speech-to-Text model

saaras:v4 is now the default model on the /speech-to-text REST, Batch and WebSocket endpoints when no model is specified. It supports the same five output modes (transcribe, translate, verbatim, translit, codemix), adds Global English alongside Indian English, and supports Keyterm Prompting. See Saaras.