@juspay/neurolink
Version:
The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002
13 lines (12 loc) • 744 B
TypeScript
/**
* The credentials slice that makes `STTProcessor.resolveHandler` build the
* provider's handler from the environment as it is NOW, rather than reuse a
* registry instance built when the process started. The OpenAI-compatible
* handler additionally honours `OPENAI_BASE_URL`, which file transcription
* (audio attachments, video audio tracks) has always followed — a gateway
* that fronts both chat and `/audio/transcriptions`; `OPENAI_STT_BASE_URL`
* still wins over it. Shared by AudioProcessor and VideoProcessor so the two
* can never resolve different endpoints.
*/
import type { STTCredentials } from "../types/index.js";
export declare function freshEnvSTTCredentials(credentialsKey: keyof STTCredentials): STTCredentials;