@juspay/neurolink/dist/adapters/audioFormatSupport.d.ts

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

/**
 * Native audio delivery to providers that can listen.
 *
 * ## The gap this closes
 *
 * Until this module existed, attaching an audio file produced a message
 * containing only a metadata block:
 *
 *   ## Audio File: "recording.mp3"
 *   Duration: 19s | Codec: MPEG 2 Layer 3 | Bitrate: 32 kbps |
 *   Sample Rate: 22050 Hz | Channels: 1 (Mono)
 *
 * No audio bytes were ever handed to the provider. Every question about what
 * the recording *says* — transcribe this, who is speaking, what was agreed —
 * was answered from a description of the file, and Gemini has accepted inline
 * audio the whole time.
 *
 * The failure was invisible for an instructive reason: that metadata block
 * answers precisely the questions a test is most tempted to ask. "How long is
 * this audio?" and "what sample rate is it?" both succeed with no audio
 * attached, so a suite built on them reports working audio support. It took an
 * end-to-end test asking for a spoken word to expose it.
 *
 * ## Provider scope
 *
 * Deliberately a capability map rather than "send audio to everyone". A
 * provider that cannot accept an audio part responds with an opaque HTTP 400,
 * which is worse than the metadata summary it would otherwise have received —
 * so an unlisted provider keeps the existing text-only behaviour and loses
 * nothing.
 *
 * @module adapters/audioFormatSupport
 */
import type { AudioConversionResult } from "../types/index.js";
/**
 * Whether `provider` can be handed raw audio bytes.
 *
 * `model` is optional and only consulted for the Vertex aliases, which serve
 * both Gemini (native audio) and Claude (no native audio — routed to
 * `@anthropic-ai/vertex-sdk`, whose message builder never reads an audio
 * part). The Claude test is the one `GoogleVertexProvider` routes by
 * (`isAnthropicModel` in providers/googleVertex/client.ts: case-insensitive,
 * anywhere in the id). A stricter test here would call a model Gemini that
 * Vertex actually sends to Claude. A caller that omits `model` on Vertex keeps
 * today's behaviour. AI Studio / bare "gemini" aliases never serve Claude.
 */
export declare function supportsNativeAudio(provider: string, model?: string): boolean;
/** Whether `mimeType` must be re-encoded before a native provider will read it. */
export declare function needsAudioTranscode(mimeType: string): boolean;
/**
 * Return audio bytes a native provider can read, transcoding when the source
 * container is one it does not accept.
 *
 * Never throws for audio reasons. When conversion is impossible — no ffmpeg, an
 * unreadable stream — the original bytes and MIME type come back with
 * `converted: false`, and the caller falls back to the metadata summary. That
 * keeps this from turning a previously-working (if limited) request into a
 * failure.
 *
 * @param buffer - Raw audio bytes.
 * @param mimeType - Detected MIME type of `buffer`.
 * @param extension - Source extension, used so ffmpeg picks the right demuxer.
 */
export declare function toProviderCompatibleAudio(buffer: Buffer, mimeType: string, extension: string): Promise<AudioConversionResult>;