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

soniox/options

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

Soniox createSoniox provider customization

The createSoniox function is used to customize the Soniox provider instance. It accepts an options object with the following properties: apiKey (override SONIOX_API_KEY), apiBaseUrl (custom API base URL for regional endpoints), headers (additional request headers), fetch (custom fetch implementation), and pollingIntervalMs (transcription polling interval in milliseconds, default 1000ms).

Soniox transcription options via providerOptions

Per-request transcription options are passed to the transcribe() function via the providerOptions parameter with a soniox key. Available options include: languageHints (array of ISO language codes to bias recognition), languageHintsStrict (rely more heavily on language hints, not supported by all models), enableLanguageIdentification (automatically detect spoken language), enableSpeakerDiarization (identify and separate different speakers), context (additional context to improve accuracy), clientReferenceId (optional client-defined reference ID), webhookUrl (webhook URL for transcription completion notifications), webhookAuthHeaderName (webhook authentication header name), webhookAuthHeaderValue (webhook authentication header value), and translation (translation configuration).

Soniox context object structure

The context object for Soniox transcription supports four optional sections: general (array of key-value pairs for domain, topic, intent, etc.), text (longer free-form background text or related documents), terms (array of domain-specific or uncommon words), and translationTerms (array of objects with source and target for custom translations of ambiguous terms).

Give your agent this brain