import { APIResource } from "../resource.js";
import * as Core from "../core.js";
import { type Response } from "../_shims/index.js";
import { Sessions, SpeechSessionParams } from "./sessions.js";
export declare class Speech extends APIResource {
    /**
     * Generates speech from text and streams the audio as binary data chunks in
     * real-time as they are generated.
     *
     * This is the recommended endpoint for most text-to-speech use cases. You can
     * either stream the chunks for low-latency playback or collect all chunks to get
     * the complete audio file.
     *
     * @example
     * ```ts
     * const response = await client.speech.generate({
     *   text: 'Uhh, did you see the weather in Palo Alto tomorrow? Yeah, can\'t believe it\'s gonna rain, dude. Like what?',
     *   voice: 'leah',
     * });
     *
     * const content = await response.blob();
     * console.log(content);
     * ```
     */
    generate(body: SpeechGenerateParams, options?: Core.RequestOptions): Core.APIPromise<Response>;
    /**
     * Generates speech from text and returns a JSON object that contains a
     * base64-encoded audio string and optionally word-level timestamps. This endpoint
     * waits for all speech to be generated before responding, so it is not ideal for
     * latency-sensitive applications.
     *
     * @example
     * ```ts
     * const response = await client.speech.generateDetailed({
     *   text: 'Uhh, did you see the weather in Palo Alto tomorrow? Yeah, can\'t believe it\'s gonna rain, dude. Like what?',
     *   voice: 'leah',
     * });
     * ```
     */
    generateDetailed(body: SpeechGenerateDetailedParams, options?: Core.RequestOptions): Core.APIPromise<SpeechGenerateDetailedResponse>;
    sessions: Sessions;
}
export interface SpeechGenerateDetailedResponse {
    /**
     * The base64-encoded audio file; the format is determined by the `format`
     * parameter.
     */
    audio: string;
    /**
     * An array describing where each generated input element (words and non-words like
     * spaces, punctuation, etc.) falls in the audio.
     */
    timestamps?: Array<SpeechGenerateDetailedResponse.Timestamp>;
}
export declare namespace SpeechGenerateDetailedResponse {
    interface Timestamp {
        /**
         * The spoken duration of the generated input element, in seconds.
         */
        duration: number;
        /**
         * The start time of the generated input element, in seconds.
         */
        start: number;
        /**
         * The generated input element; beginning and ending with a short silence.
         */
        text: string;
    }
}
export interface SpeechGenerateParams {
    /**
     * The text to generate speech from; max 5000 characters per request (including
     * spaces).
     */
    text: string;
    /**
     * The voice id of the voice to use; voice ids can be retrieved by calls to
     * `List voices` or `Voice info`.
     */
    voice: string;
    /**
     * When set to true, the generated speech will also be saved to your
     * [clip library](https://app.lmnt.com/clips) in the LMNT playground.
     */
    debug?: boolean;
    /**
     * The desired output format of the audio. If you are using a streaming endpoint,
     * you'll generate audio faster by selecting a streamable format since chunks are
     * encoded and returned as they're generated. For non-streamable formats, all
     * speech will be generated before encoding.
     *
     * Streamable formats:
     *
     * - `mp3`: 96kbps MP3 audio.
     * - `ulaw`: 8-bit G711 µ-law audio with a WAV header.
     * - `webm`: WebM format with Opus audio codec.
     * - `pcm_s16le`: PCM signed 16-bit little-endian audio.
     * - `pcm_f32le`: PCM 32-bit floating-point little-endian audio.
     *
     * Non-streamable formats:
     *
     * - `aac`: AAC audio codec.
     * - `wav`: 16-bit PCM audio in WAV container.
     */
    format?: 'aac' | 'mp3' | 'ulaw' | 'wav' | 'webm' | 'pcm_s16le' | 'pcm_f32le';
    /**
     * The desired language. Two letter ISO 639-1 code. Defaults to auto language
     * detection, but specifying the language is recommended for faster generation.
     */
    language?: 'auto' | 'ar' | 'as' | 'bn' | 'cs' | 'da' | 'de' | 'en' | 'es' | 'fi' | 'fr' | 'hi' | 'id' | 'it' | 'ja' | 'ko' | 'ml' | 'mr' | 'nl' | 'pl' | 'pt' | 'ru' | 'sk' | 'sv' | 'ta' | 'te' | 'th' | 'tr' | 'uk' | 'ur' | 'vi' | 'zh';
    /**
     * The model to use for speech generation. Learn more about models
     * [here](https://docs.lmnt.com/models/overview).
     */
    model?: 'blizzard';
    /**
     * The desired output sample rate in Hz. Defaults to `24000` for all formats except
     * `mulaw` which defaults to `8000`.
     */
    sample_rate?: 8000 | 16000 | 24000;
    /**
     * Influences how expressive and emotionally varied the speech becomes. Lower
     * values (like 0.3) create more neutral, consistent speaking styles. Higher values
     * (like 1.0) allow for more dynamic emotional range and speaking styles.
     */
    temperature?: number;
    /**
     * Controls the stability of the generated speech. A lower value (like 0.3)
     * produces more consistent, reliable speech. A higher value (like 0.9) gives more
     * flexibility in how words are spoken, but might occasionally produce unusual
     * intonations or speech patterns.
     */
    top_p?: number;
}
export interface SpeechGenerateDetailedParams {
    /**
     * The text to generate speech from; max 5000 characters per request (including
     * spaces).
     */
    text: string;
    /**
     * The voice id of the voice to use; voice ids can be retrieved by calls to
     * `List voices` or `Voice info`.
     */
    voice: string;
    /**
     * When set to true, the generated speech will also be saved to your
     * [clip library](https://app.lmnt.com/clips) in the LMNT playground.
     */
    debug?: boolean;
    /**
     * The desired output format of the audio. If you are using a streaming endpoint,
     * you'll generate audio faster by selecting a streamable format since chunks are
     * encoded and returned as they're generated. For non-streamable formats, all
     * speech will be generated before encoding.
     *
     * Streamable formats:
     *
     * - `mp3`: 96kbps MP3 audio.
     * - `ulaw`: 8-bit G711 µ-law audio with a WAV header.
     * - `webm`: WebM format with Opus audio codec.
     * - `pcm_s16le`: PCM signed 16-bit little-endian audio.
     * - `pcm_f32le`: PCM 32-bit floating-point little-endian audio.
     *
     * Non-streamable formats:
     *
     * - `aac`: AAC audio codec.
     * - `wav`: 16-bit PCM audio in WAV container.
     */
    format?: 'aac' | 'mp3' | 'ulaw' | 'wav' | 'webm' | 'pcm_s16le' | 'pcm_f32le';
    /**
     * The desired language. Two letter ISO 639-1 code. Defaults to auto language
     * detection, but specifying the language is recommended for faster generation.
     */
    language?: 'auto' | 'ar' | 'as' | 'bn' | 'cs' | 'da' | 'de' | 'en' | 'es' | 'fi' | 'fr' | 'hi' | 'id' | 'it' | 'ja' | 'ko' | 'ml' | 'mr' | 'nl' | 'pl' | 'pt' | 'ru' | 'sk' | 'sv' | 'ta' | 'te' | 'th' | 'tr' | 'uk' | 'ur' | 'vi' | 'zh';
    /**
     * The model to use for speech generation. Learn more about models
     * [here](https://docs.lmnt.com/models/overview).
     */
    model?: 'blizzard';
    /**
     * If set as `true`, the response will contain a `timestamps` array describing
     * where each input element falls in the generated audio.
     */
    return_timestamps?: boolean;
    /**
     * The desired output sample rate in Hz. Defaults to `24000` for all formats except
     * `mulaw` which defaults to `8000`.
     */
    sample_rate?: 8000 | 16000 | 24000;
    /**
     * Influences how expressive and emotionally varied the speech becomes. Lower
     * values (like 0.3) create more neutral, consistent speaking styles. Higher values
     * (like 1.0) allow for more dynamic emotional range and speaking styles.
     */
    temperature?: number;
    /**
     * Controls the stability of the generated speech. A lower value (like 0.3)
     * produces more consistent, reliable speech. A higher value (like 0.9) gives more
     * flexibility in how words are spoken, but might occasionally produce unusual
     * intonations or speech patterns.
     */
    top_p?: number;
}
export declare namespace Speech {
    export { type SpeechGenerateDetailedResponse as SpeechGenerateDetailedResponse, type SpeechGenerateParams as SpeechGenerateParams, type SpeechGenerateDetailedParams as SpeechGenerateDetailedParams, };
    export { Sessions as Sessions, type SpeechSessionParams as SpeechSessionParams };
}
//# sourceMappingURL=speech.d.ts.map