@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
22 lines (21 loc) • 966 B
TypeScript
/**
* Transport-agnostic voice brain.
*
* Given a user transcript and a stable conversation id, it streams the
* assistant's reply as text deltas by calling `neurolink.stream()`. NeuroLink
* owns history (via the conversation id and its memory layer) and tools (the
* tool-calling loop runs inside `stream()`); this module never touches a
* transport. The LiveKit worker (or any other transport) consumes the text
* deltas and converts them to audio.
*
* See docs/features/livekit-voice-agent.md.
*/
import type { LiveKitBrainConfig, LiveKitVoiceBrain } from "../../types/index.js";
/**
* Create a voice brain bound to a configured NeuroLink instance.
*
* The returned `streamReply` is an async generator of text deltas for a single
* turn. Aborting `turn.signal` stops the in-flight LLM and tool calls and ends
* the generator promptly (barge-in support).
*/
export declare function createVoiceBrain(config: LiveKitBrainConfig): LiveKitVoiceBrain;