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

fal/transcription

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.

Fal transcription model factory method

Create Fal transcription models using the .transcription() factory method. The first argument is the model id without the fal-ai/ prefix. Example: const model = fal.transcription('wizper');

Fal transcription basic example with provider options

Example of Fal transcription with provider options: import { transcribe } from 'ai'; import { fal, type FalTranscriptionModelOptions } from '@ai-sdk/fal'; import { readFile } from 'fs/promises'; const result = await transcribe({ model: fal.transcription('wizper'), audio: await readFile('audio.mp3'), providerOptions: { fal: { batchSize: 10 } satisfies FalTranscriptionModelOptions, }, });

Fal transcription provider options

Fal transcription models support these provider options: (1) language (string) - Language of the audio file. Defaults to 'en'. If set to null, language will be automatically detected. Accepts ISO language codes like 'en', 'fr', 'zh', etc. Optional. (2) diarize (boolean) - Whether to diarize the audio file (identify different speakers). Defaults to true. Optional. (3) chunkLevel (string) - Level of the chunks to return: 'segment' or 'word'. Default value: 'segment'. Optional. (4) version (string) - Version of the model to use. All models are Whisper large variants. Default value: '3'. Optional. (5) batchSize (number) - Batch size for processing. Default value: 64. Optional. (6) numSpeakers (number) - Number of speakers in the audio file. If not provided, will be automatically detected. Optional.

Fal transcription models capabilities

Fal transcription models: (1) whisper - Supports transcription, duration, segments, language. (2) wizper - Supports transcription, duration, segments, language.

Give your agent this brain