import { TTS } from '../../agents/providers.js';
import type { CartesiaTTSModel } from './models.js';
declare class GenerationConfigImpl {
    static readonly displayName = "GenerationConfig";
    speed: number | null;
    emotion: string | null;
    volume: number | null;
    pronunciationDictId: string | null;
    maxBufferDelayMs: number | null;
    enableWordTimestamps: boolean;
    constructor(opts?: {
        speed?: number | null;
        emotion?: string | null;
        volume?: number | null;
        pronunciationDictId?: string | null;
        maxBufferDelayMs?: number | null;
        enableWordTimestamps?: boolean;
    });
}
export type GenerationConfig = GenerationConfigImpl;
/**
 * Grouped generation settings for {@link CartesiaTTS}. Flat options on
 * `CartesiaTTSOptions` take precedence over the matching field here.
 *
 * @param opts.speed Speaking speed. Default: `null`.
 * @param opts.emotion Emotion tag to apply. Default: `null`.
 * @param opts.volume Output volume. Default: `null`.
 * @param opts.pronunciationDictId Pronunciation dictionary ID. Default: `null`.
 * @param opts.maxBufferDelayMs Max buffering delay in ms. Default: `null`.
 * @param opts.enableWordTimestamps Emit per-word timestamps. Default: `false`.
 */
export declare const GenerationConfig: (opts?: {
    speed?: number | null;
    emotion?: string | null;
    volume?: number | null;
    pronunciationDictId?: string | null;
    maxBufferDelayMs?: number | null;
    enableWordTimestamps?: boolean;
}) => GenerationConfig;
/** Configuration options for the {@link CartesiaTTS} provider. */
export type CartesiaTTSOptions = {
    /** Cartesia API key. Falls back to the `CARTESIA_API_KEY` env var. */
    apiKey?: string;
    /** Voice as a catalog UUID (string) or a cloning embedding (non-empty number array). Default: a built-in voice UUID. */
    voice?: string | number[] | null;
    /** Alias for `voice`; used when `voice` is not set. */
    voiceId?: string | number[] | null;
    /** Synthesis model. Default: `'sonic-2'`. */
    model?: CartesiaTTSModel | string;
    /** Synthesis language code. Default: `'en'`. */
    language?: string;
    /** Output audio sample rate in Hz. Default: `24000`. (The effective rate is fixed; other values are ignored.) */
    sampleRate?: number;
    /** Speaking speed. Default: `null` (or `generationConfig.speed`). */
    speed?: number | null;
    /** Output volume. Default: `null` (or `generationConfig.volume`). */
    volume?: number | null;
    /** Emotion tag. Default: `null` (or `generationConfig.emotion`). */
    emotion?: string | null;
    /** Pronunciation dictionary ID. Default: `null` (or `generationConfig.pronunciationDictId`). */
    pronunciationDictId?: string | null;
    /** Max buffering delay in ms. Default: `null` (or `generationConfig.maxBufferDelayMs`). */
    maxBufferDelayMs?: number | null;
    /** Emit per-word timestamps. Default: `false` (or `generationConfig.enableWordTimestamps`). */
    enableWordTimestamps?: boolean | null;
    /** Grouped generation settings; flat options above take precedence. Default: `null`. */
    generationConfig?: GenerationConfig | null;
    [key: string]: any;
};
declare class CartesiaTTSImpl extends TTS {
    static readonly displayName = "CartesiaTTS";
    _providerName: string;
    apiKey?: string;
    voiceId: string;
    voice: string;
    voiceEmbedding: number[] | null;
    model: string;
    language: string;
    speed: number | null;
    volume: number | null;
    emotion: string | null;
    pronunciationDictId: string | null;
    maxBufferDelayMs: number | null;
    enableWordTimestamps: boolean;
    constructor(opts?: CartesiaTTSOptions);
    getRuntimeConfig(): Record<string, any>;
}
export type CartesiaTTS = CartesiaTTSImpl;
/**
 * Cartesia text-to-speech provider.
 *
 * Creates a configured Cartesia TTS provider for use in a voice agent.
 */
export declare const CartesiaTTS: (opts?: CartesiaTTSOptions) => CartesiaTTS;
export {};