/*
 * Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.
 */

import { llmSpeechDeleteTranscriptionHistory } from "../funcs/llmSpeechDeleteTranscriptionHistory.js";
import { llmSpeechDeleteTtsHistory } from "../funcs/llmSpeechDeleteTtsHistory.js";
import { llmSpeechGetTranscriptionHistory } from "../funcs/llmSpeechGetTranscriptionHistory.js";
import { llmSpeechGetTranscriptionHistoryContent } from "../funcs/llmSpeechGetTranscriptionHistoryContent.js";
import { llmSpeechGetTtsHistory } from "../funcs/llmSpeechGetTtsHistory.js";
import {
  GetTtsHistoryContentAcceptEnum,
  llmSpeechGetTtsHistoryContent,
} from "../funcs/llmSpeechGetTtsHistoryContent.js";
import { llmSpeechListTranscriptionHistory } from "../funcs/llmSpeechListTranscriptionHistory.js";
import { llmSpeechListTtsHistory } from "../funcs/llmSpeechListTtsHistory.js";
import { llmSpeechLivekitToken } from "../funcs/llmSpeechLivekitToken.js";
import { llmSpeechSpeak } from "../funcs/llmSpeechSpeak.js";
import {
  llmSpeechSpeakStreaming,
  SpeakStreamingAcceptEnum,
} from "../funcs/llmSpeechSpeakStreaming.js";
import { llmSpeechTranscribe } from "../funcs/llmSpeechTranscribe.js";
import { ClientSDK, RequestOptions } from "../lib/sdks.js";
import * as components from "../models/components/index.js";
import * as operations from "../models/operations/index.js";
import { unwrapAsync } from "../types/fp.js";

export { SpeakStreamingAcceptEnum } from "../funcs/llmSpeechSpeakStreaming.js";

export { GetTtsHistoryContentAcceptEnum } from "../funcs/llmSpeechGetTtsHistoryContent.js";

export class Speech extends ClientSDK {
  /**
   * Speech to text transcription
   *
   * @remarks
   * Convert audio to text using advanced speech recognition.
   *
   * **Complete File Upload (Standard)**
   * Use `Content-Type: multipart/form-data` to upload the complete audio file in one request. Maximum file size: 25MB.
   *
   * Example:
   * ```bash
   * curl -X POST "http://localhost:3000/api/v1/llm/speech/transcriptions?language=en" \
   *   -F "file=@audio.flac"
   * ```
   *
   * **Chunked Upload (Streaming)**
   * Use `Transfer-Encoding: chunked` header to stream audio data in chunks as it's being recorded. No need to know total file size upfront. Server buffers chunks until complete before processing. Maximum total size: 25MB.
   *
   * Example:
   * ```bash
   * curl -X POST "http://localhost:3000/api/v1/llm/speech/transcriptions?language=en" \
   *   -H "Transfer-Encoding: chunked" \
   *   -H "Content-Type: multipart/form-data" \
   *   --data-binary @audio.flac
   * ```
   *
   * **Supported Formats:** FLAC, MP3, MP4, MPEG, MPGA, M4A, OGG, WAV, WebM
   *
   * **Query Parameters:**
   * - `model` (optional): Transcription model identifier. Defaults to 'auto'.
   * - `language` (optional): ISO-639-1 or BCP-47 language code (e.g., "en", "en-US"). Auto-detects if not specified.
   * - `prompt` (optional): Legacy prompt parameter retained for backward compatibility.
   * - `temperature` (optional): Legacy temperature parameter retained for backward compatibility.
   * - `include_speaker_data` (optional): When `true`, include speaker diarization data and require WAV/PCM input. Otherwise transcription uses the standard compatibility path.
   *
   * **Response:** Returns transcribed text in JSON format.
   */
  async transcribe(
    request: operations.TranscribeRequest,
    options?: RequestOptions,
  ): Promise<components.TranscriptionResponse> {
    return unwrapAsync(llmSpeechTranscribe(
      this,
      request,
      options,
    ));
  }

  /**
   * Text to speech
   *
   * @remarks
   * Convert text to speech with automatic language detection.
   *
   * **Request Body:**
   * - `text`: Input text to convert to speech - required
   * - `language`: Language code (default: "auto") - "auto" for automatic detection, or ISO 639-1 codes: en, zh, hi, es, ar, bn, pt, ru, ja, pa, de, ko, fr, tr, it, th, pl, nl, id, vi, ur
   * - `model`: TTS model identifier (default: "auto") - "auto" selects the default provider; a registry-resolvable id dispatches to the matching provider
   *
   * **Response:** Returns audio file in WAV format with X-Language-Code header. When `store` is `true`, the generation is persisted before the response returns and the new history record id is included in the X-Tts-Id header.
   */
  async speak(
    request: operations.TextToSpeechRequest,
    options?: RequestOptions,
  ): Promise<operations.TextToSpeechResponse> {
    return unwrapAsync(llmSpeechSpeak(
      this,
      request,
      options,
    ));
  }

  /**
   * Streaming text to speech
   *
   * @remarks
   * Convert text to speech with real-time streaming audio delivery.
   *
   * **Key Features:**
   * - Low-latency audio streaming - playback can start immediately as chunks arrive
   * - Automatic language detection
   * - Multiple format support: MP3 or PCM/WAV
   * - High-quality audio: 24kHz sample rate, 16-bit mono
   *
   * **Request Body:**
   * - `text`: Input text to convert to speech - required
   * - `language`: Language code (default: "auto") - "auto" for automatic detection, or ISO 639-1 codes: en, zh, hi, es, ar, bn, pt, ru, ja, pa, de, ko, fr, tr, it, th, pl, nl, id, vi, ur
   * - `format`: Audio format (default: "mp3") - "mp3" for compressed MPEG audio (96 kbps) or "pcm" for uncompressed WAV
   * - `model`: TTS model identifier (default: "auto") - "auto" selects the default provider; a registry-resolvable id dispatches to the matching provider (note: not all providers support `format: "mp3"`)
   *
   * **Response:**
   * - Streams audio chunks in real-time
   * - Returns `X-Language-Code` header with detected/used language
   * - Content-Type: `audio/mpeg` (MP3) or `audio/wav` (PCM)
   * - When `store` is `true`, returns the `X-Tts-Id` header with the id the history record will be stored under; persistence is best-effort and completes shortly after the stream ends
   *
   * **Use Cases:**
   * - Real-time applications requiring immediate audio playback
   * - Interactive voice responses
   * - Low-latency text-to-speech scenarios
   */
  async speakStreaming(
    request: operations.TextToSpeechStreamingRequest,
    options?: RequestOptions & {
      acceptHeaderOverride?: SpeakStreamingAcceptEnum;
    },
  ): Promise<operations.TextToSpeechStreamingResponse> {
    return unwrapAsync(llmSpeechSpeakStreaming(
      this,
      request,
      options,
    ));
  }

  /**
   * Generate LiveKit room token
   *
   * @remarks
   * Generates a LiveKit access token for joining a real-time voice room. The token includes encrypted credentials and model configuration for the voice agent.
   */
  async livekitToken(
    request: operations.LivekitTokenRequest,
    options?: RequestOptions,
  ): Promise<components.LivekitTokenResponse> {
    return unwrapAsync(llmSpeechLivekitToken(
      this,
      request,
      options,
    ));
  }

  /**
   * List text-to-speech history
   *
   * @remarks
   * List stored text-to-speech generations for the authenticated user, newest first by default.
   */
  async listTtsHistory(
    request: operations.ListTextToSpeechHistoryRequest,
    options?: RequestOptions,
  ): Promise<components.TextToSpeechHistoryList> {
    return unwrapAsync(llmSpeechListTtsHistory(
      this,
      request,
      options,
    ));
  }

  /**
   * Retrieve text-to-speech history item
   *
   * @remarks
   * Returns metadata for a stored text-to-speech generation.
   */
  async getTtsHistory(
    request: operations.GetTextToSpeechHistoryRequest,
    options?: RequestOptions,
  ): Promise<components.TextToSpeechHistoryObject> {
    return unwrapAsync(llmSpeechGetTtsHistory(
      this,
      request,
      options,
    ));
  }

  /**
   * Delete text-to-speech history item
   *
   * @remarks
   * Deletes a stored text-to-speech generation. The audio blob is content-addressed and may be shared, so it is left in storage.
   */
  async deleteTtsHistory(
    request: operations.DeleteTextToSpeechHistoryRequest,
    options?: RequestOptions,
  ): Promise<components.SpeechHistoryDeletionStatus> {
    return unwrapAsync(llmSpeechDeleteTtsHistory(
      this,
      request,
      options,
    ));
  }

  /**
   * Retrieve text-to-speech audio
   *
   * @remarks
   * Returns the stored audio for a text-to-speech generation as a binary response.
   */
  async getTtsHistoryContent(
    request: operations.GetTextToSpeechHistoryContentRequest,
    options?: RequestOptions & {
      acceptHeaderOverride?: GetTtsHistoryContentAcceptEnum;
    },
  ): Promise<operations.GetTextToSpeechHistoryContentResponse> {
    return unwrapAsync(llmSpeechGetTtsHistoryContent(
      this,
      request,
      options,
    ));
  }

  /**
   * List speech-to-text history
   *
   * @remarks
   * List stored transcriptions for the authenticated user, newest first by default.
   */
  async listTranscriptionHistory(
    request: operations.ListSpeechToTextHistoryRequest,
    options?: RequestOptions,
  ): Promise<components.SpeechToTextHistoryList> {
    return unwrapAsync(llmSpeechListTranscriptionHistory(
      this,
      request,
      options,
    ));
  }

  /**
   * Retrieve speech-to-text history item
   *
   * @remarks
   * Returns metadata for a stored transcription.
   */
  async getTranscriptionHistory(
    request: operations.GetSpeechToTextHistoryRequest,
    options?: RequestOptions,
  ): Promise<components.SpeechToTextHistoryObject> {
    return unwrapAsync(llmSpeechGetTranscriptionHistory(
      this,
      request,
      options,
    ));
  }

  /**
   * Delete speech-to-text history item
   *
   * @remarks
   * Deletes a stored transcription. The audio blob is content-addressed and may be shared, so it is left in storage.
   */
  async deleteTranscriptionHistory(
    request: operations.DeleteSpeechToTextHistoryRequest,
    options?: RequestOptions,
  ): Promise<components.SpeechHistoryDeletionStatus> {
    return unwrapAsync(llmSpeechDeleteTranscriptionHistory(
      this,
      request,
      options,
    ));
  }

  /**
   * Retrieve speech-to-text audio
   *
   * @remarks
   * Returns the stored input audio for a transcription as a binary response.
   */
  async getTranscriptionHistoryContent(
    request: operations.GetSpeechToTextHistoryContentRequest,
    options?: RequestOptions,
  ): Promise<ReadableStream<Uint8Array>> {
    return unwrapAsync(llmSpeechGetTranscriptionHistoryContent(
      this,
      request,
      options,
    ));
  }
}