new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

cartesia/models

5 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Cartesia speech model creation

Create speech models using the .speech() factory method with a model id argument, e.g., cartesia.speech('sonic-3.5'). Use with the generateSpeech function and requires a voice id parameter.

Cartesia speech model IDs

Cartesia speech models available: sonic-3.5, sonic-3, sonic-2, sonic-turbo, sonic-latest.

Cartesia realtime transcription model creation

Create realtime transcription models using the .experimental_realtime() factory method with model id 'ink-2'. Realtime is an experimental feature.

Cartesia streaming transcription model creation

Create streaming transcription models using the .transcription() factory method with model id 'ink-2'. Use with experimental_streamTranscribe function. Streaming transcription is an experimental feature.

Cartesia batch transcription model creation

Create batch transcription models using the .transcription() factory method with model id 'ink-whisper'. Use with the transcribe function.

Give your agent this brain