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

deepgram/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.

Deepgram speech model creation

Speech models are created using the .speech() factory method on the deepgram provider. The model ID includes the voice directly embedded (e.g., 'aura-2-helena-en').

Deepgram speech models list

Available Deepgram speech models include: aura-2-asteria-en, aura-2-thalia-en, aura-2-helena-en, aura-2-orpheus-en, aura-2-zeus-en, aura-asteria-en, aura-luna-en, aura-stella-en, and more voices available in the Deepgram documentation.

Deepgram transcription model creation

Transcription models are created using the .transcription() factory method on the deepgram provider. The model ID specifies the model version (e.g., 'nova-3').

Deepgram transcription models list

Available Deepgram transcription models include: nova-3, nova-2, nova, enhanced, and base. Each model has variants available.

Deepgram speech API usage example

Speech generation example: import { generateSpeech } from 'ai'; import { deepgram } from '@ai-sdk/deepgram'; const result = await generateSpeech({ model: deepgram.speech('aura-2-helena-en'), text: 'Hello, world!', });

Give your agent this brain