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

sarvam/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.

Sarvam language_code option

The `language_code` option specifies the language of the input audio. It is mandatory for the `saarika:v1` model and optional for `saarika:v2`. Use `unknown` to enable auto-detection. Available options: `unknown`, `hi-IN`, `bn-IN`, `kn-IN`, `ml-IN`, `mr-IN`, `od-IN`, `pa-IN`, `ta-IN`, `te-IN`, `en-IN`, `gu-IN`. Required for accurate transcription.

Sarvam with_timestamps option

The `with_timestamps` option is a boolean (default: false) that specifies whether to include start/end timestamps for each word/token in the transcription output.

Sarvam with_diarization option

The `with_diarization` option is a boolean (default: false, Beta feature) that enables speaker diarization to distinguish different speakers in the audio.

Sarvam num_speakers option

The `num_speakers` option is a number or null (default: null) that sets the number of distinct speakers to detect. This option only applies when `with_diarization` is true.

Give your agent this brain