/**
 * Configuration message required as the first message after establishing the WebSocket connection.
 * Pass **exactly one** of `voice_id` (saved voice) or `ref_audio` (base64 reference clip).
 * `target_language_code` is optional: omit it to detect the language from the first
 * buffered text, then that language stays locked until the next config.
 * Optional `ref_text` improves fidelity when using `ref_audio`.
 * Sending both `voice_id` and `ref_audio` returns an error. Duration bounds, QC, and VAD
 * are not accepted on this path.
 */
export interface VoiceCloningConfigureConnection {
    type: "config";
    data: VoiceCloningConfigureConnection.Data;
}
export declare namespace VoiceCloningConfigureConnection {
    interface Data {
        /**
         * BCP-47 language code for the synthesized output. The cloned voice can speak any
         * supported language, regardless of the reference clip's language. Omit it to
         * detect the language from the first buffered text. Detection is locked for the
         * rest of the session; send a new config with an explicit code to change language.
         * Detection can be wrong on short or code-mixed text. Romanized Indic and Urdu
         * return 400. Short Assamese without ৰ or ৱ is often detected as Bengali — pass
         * `as-IN`.
         */
        target_language_code?: Data.TargetLanguageCode | undefined;
        /**
         * Cloned voice ID (`svc-{uuid}`) from your voice library. Create one with
         * `POST /voices/create`. Exactly one of `voice_id` or `ref_audio` must be provided.
         */
        voice_id?: string | undefined;
        /**
         * Base64-encoded reference audio clip (WAV recommended; also MP3, FLAC, OPUS, AAC,
         * MULAW, ALAW, LINEAR16). Max 10 MB decoded size and 15 seconds. Exactly one of
         * `voice_id` or `ref_audio` must be provided.
         */
        ref_audio?: string | undefined;
        /**
         * Optional transcript of `ref_audio` (max 500 characters). Improves fidelity.
         * Omit to let the API transcribe the clip. Ignored when `voice_id` is used.
         */
        ref_text?: string | undefined;
        /** Speech speed (0.5–2.0). 1.0 = natural speed. */
        pace?: number | undefined;
        /** Output sample rate in Hz. */
        speech_sample_rate?: number | undefined;
        /**
         * Pre-TTS text normalization: numbers, currencies and dates converted to spoken
         * form before synthesis. Defaults to the server-side setting.
         */
        enable_pretts?: boolean | undefined;
        /**
         * Remove background noise from the uploaded reference audio before synthesis.
         * Only applies when `ref_audio` is provided; ignored for `voice_id`.
         * Adds processing latency before the first audio chunk -- roughly 1 second
         * for a typical reference clip.
         */
        remove_background_noise?: boolean | undefined;
        /**
         * Audio codec for streamed frames. Default is `mp3`.
         * Allowed: `mp3`, `wav`, `linear16`, `mulaw`, `alaw`.
         */
        output_audio_codec?: Data.OutputAudioCodec | undefined;
        /** Bitrate for lossy codecs. Default is `128k`. */
        output_audio_bitrate?: Data.OutputAudioBitrate | undefined;
        /** Minimum character length that triggers buffer flushing for synthesis. */
        min_buffer_size?: number | undefined;
        /** Maximum length for sentence splitting. */
        max_chunk_length?: number | undefined;
    }
    namespace Data {
        /**
         * BCP-47 language code for the synthesized output. The cloned voice can speak any
         * supported language, regardless of the reference clip's language. Omit it to
         * detect the language from the first buffered text. Detection is locked for the
         * rest of the session; send a new config with an explicit code to change language.
         * Detection can be wrong on short or code-mixed text. Romanized Indic and Urdu
         * return 400. Short Assamese without ৰ or ৱ is often detected as Bengali — pass
         * `as-IN`.
         */
        const TargetLanguageCode: {
            readonly AsIn: "as-IN";
            readonly BnIn: "bn-IN";
            readonly EnIn: "en-IN";
            readonly GuIn: "gu-IN";
            readonly HiIn: "hi-IN";
            readonly KnIn: "kn-IN";
            readonly MlIn: "ml-IN";
            readonly MrIn: "mr-IN";
            readonly OdIn: "od-IN";
            readonly PaIn: "pa-IN";
            readonly TaIn: "ta-IN";
            readonly TeIn: "te-IN";
        };
        type TargetLanguageCode = (typeof TargetLanguageCode)[keyof typeof TargetLanguageCode];
        /**
         * Audio codec for streamed frames. Default is `mp3`.
         * Allowed: `mp3`, `wav`, `linear16`, `mulaw`, `alaw`.
         */
        const OutputAudioCodec: {
            readonly Mp3: "mp3";
            readonly Wav: "wav";
            readonly Linear16: "linear16";
            readonly Mulaw: "mulaw";
            readonly Alaw: "alaw";
        };
        type OutputAudioCodec = (typeof OutputAudioCodec)[keyof typeof OutputAudioCodec];
        /** Bitrate for lossy codecs. Default is `128k`. */
        const OutputAudioBitrate: {
            readonly ThirtyTwoK: "32k";
            readonly SixtyFourK: "64k";
            readonly NinetySixK: "96k";
            readonly OneHundredTwentyEightK: "128k";
            readonly OneHundredNinetyTwoK: "192k";
        };
        type OutputAudioBitrate = (typeof OutputAudioBitrate)[keyof typeof OutputAudioBitrate];
    }
}