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/options

4 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 options

Speech model provider options include: encoding (supported values: 'linear16', 'mulaw', 'alaw', 'mp3', 'opus', 'flac', 'aac'), container (supported values: 'wav', 'ogg', 'none'), sampleRate (supported values: 8000, 16000, 24000, 32000, 48000 Hz depending on encoding), bitRate (number or string: 32000 or 48000 for mp3, 4000 to 650000 for opus, 4000 to 192000 for aac), callback (URL for callback requests), callbackMethod (enum: 'POST' or 'PUT'), mipOptOut (boolean to opt out of Model Improvement Program), and tag (string or array of strings for labeling requests). All are optional.

Deepgram transcription model options

Transcription model provider options include: language (ISO-639-1 and ISO-639-3 language codes), detectLanguage (boolean for automatic language detection), smartFormat (boolean for smart formatting), punctuate (boolean to add punctuation), summarize (enum or boolean with allowed values 'v2' or false), topics (boolean to detect topics), detectEntities (boolean to detect entities), redact (string or array of strings for content redaction), search (string for finding terms in transcription), diarize (boolean for speaker identification, defaults to true), utterances (boolean for utterance segmentation), uttSplit (number for utterance splitting threshold), and fillerWords (boolean to include filler words). All are optional.

Deepgram speech with provider options example

Speech with custom options example: import { generateSpeech } from 'ai'; import { deepgram, type DeepgramSpeechModelOptions } from '@ai-sdk/deepgram'; const result = await generateSpeech({ model: deepgram.speech('aura-2-helena-en'), text: 'Hello, world!', providerOptions: { deepgram: { encoding: 'linear16', sampleRate: 24000, } satisfies DeepgramSpeechModelOptions, }, });

Deepgram transcription API usage example

Transcription example: import { transcribe } from 'ai'; import { deepgram, type DeepgramTranscriptionModelOptions } from '@ai-sdk/deepgram'; import { readFile } from 'fs/promises'; const result = await transcribe({ model: deepgram.transcription('nova-3'), audio: await readFile('audio.mp3'), providerOptions: { deepgram: { summarize: true, } satisfies DeepgramTranscriptionModelOptions, }, });

Give your agent this brain