/** * Transcript beats — turn a timed transcript (SRT / WebVTT / whisper JSON) * into ~5s, pause-aware beats, and seed a coverage-only motion-pack skeleton * from them. The VO is the timeline: every beat eventually gets a decision * (generated / v2v / talking-head / screen-rec / reuse). * * Pure text-in, data-out — no transcription here. Media without a transcript * goes through existing STT tooling first. */ import type { MotionPackArtifact, TranscriptBeat } from './types.js'; export interface TranscriptCue { t0Sec: number; t1Sec: number; text: string; } /** A gap this long between cues is a hard pause — a natural clip boundary. */ export declare const DEFAULT_PAUSE_GAP_SEC = 0.8; export declare const DEFAULT_BEAT_TARGET_SEC = 5; export declare function parseSrt(text: string): TranscriptCue[]; export declare function parseVtt(text: string): TranscriptCue[]; export declare function parseWhisperJson(text: string): TranscriptCue[]; export declare function parseTranscriptCues(content: string, fileName: string): TranscriptCue[]; /** * Merge cues into ~targetSec beats, never straddling a hard pause. Beats are * the unit blocks map onto; a pause after a beat marks a natural boundary a * block should not cross. */ export declare function buildBeats(cues: TranscriptCue[], opts?: { targetSec?: number; pauseGapSec?: number; }): TranscriptBeat[]; /** * Seed a coverage-only pack skeleton from beats: rows are topic chunks split * at hard pauses (capped near SEGMENT_TARGET_SEC), every row defaulting to * `talking-head` — the authoring pass upgrades rows to generated/v2v and adds * blocks. Blocks start empty on purpose: choreography is a creative decision. */ export declare function initPackFromBeats(beats: TranscriptBeat[], opts: { projectSlug: string; video: string; sheetId: string; generatedAt: string; aspect?: string; durationSec?: number; }): MotionPackArtifact; //# sourceMappingURL=beats.d.ts.map