export type TTSModelID = 'sonic-3.5' | 'sonic-3' | 'sonic-latest';

export type VoiceId = string;

export type TTSRequestVoiceSpecifier = {mode: 'id', id: VoiceId};

export type SupportedLanguage = 'en' | 'fr' | 'de' | 'es' | 'pt' | 'zh' | 'ja' | 'hi' | 'it' | 'ko' | 'nl' | 'pl' | 'ru' | 'sv' | 'tr' | 'tl' | 'bg' | 'ro' | 'ar' | 'cs' | 'el' | 'fi' | 'hr' | 'ms' | 'sk' | 'da' | 'ta' | 'uk' | 'hu' | 'no' | 'vi' | 'bn' | 'th' | 'he' | 'ka' | 'id' | 'te' | 'gu' | 'kn' | 'ml' | 'mr' | 'pa';

export type RawEncoding = 'pcm_f32le' | 'pcm_s16le' | 'pcm_mulaw' | 'pcm_alaw';

export type OutputFormat = {container: 'wav', encoding: RawEncoding, sample_rate: 8000 | 16000 | 22050 | 24000 | 44100 | 48000} | {container: 'mp3', sample_rate: 8000 | 16000 | 22050 | 24000 | 44100 | 48000, bit_rate: 32000 | 64000 | 96000 | 128000 | 192000} | {container: 'raw', encoding: RawEncoding, sample_rate: 8000 | 16000 | 22050 | 24000 | 44100 | 48000};

export type Emotion = 'neutral' | 'happy' | 'excited' | 'enthusiastic' | 'elated' | 'euphoric' | 'triumphant' | 'amazed' | 'surprised' | 'flirtatious' | 'curious' | 'content' | 'peaceful' | 'serene' | 'calm' | 'grateful' | 'affectionate' | 'trust' | 'sympathetic' | 'anticipation' | 'mysterious' | 'angry' | 'mad' | 'outraged' | 'frustrated' | 'agitated' | 'threatened' | 'disgusted' | 'contempt' | 'envious' | 'sarcastic' | 'ironic' | 'sad' | 'dejected' | 'melancholic' | 'disappointed' | 'hurt' | 'guilty' | 'bored' | 'tired' | 'rejected' | 'nostalgic' | 'wistful' | 'apologetic' | 'hesitant' | 'insecure' | 'confused' | 'resigned' | 'anxious' | 'panicked' | 'alarmed' | 'scared' | 'proud' | 'confident' | 'distant' | 'skeptical' | 'contemplative' | 'determined';

export type GenerationConfig = {volume?: number | undefined, speed?: number | undefined, emotion?: Emotion | undefined};

export type ModelSpeed = 'slow' | 'normal' | 'fast';

export type TTSRequest = {model_id: TTSModelID, transcript: string, voice: TTSRequestVoiceSpecifier, language?: SupportedLanguage | undefined, output_format: OutputFormat, pronunciation_dict_id?: (string | null) | undefined, generation_config?: GenerationConfig | undefined, speed?: ModelSpeed | undefined};

export type CreateApiTtsBytesArgs = {'Cartesia-Version': '2026-03-01', body: TTSRequest};

export type CreateApiTtsBytesOptions = {baseUrl?: string | undefined, APIKeyAuth?: string | undefined, fetch?: typeof fetch | undefined};

/**
 * Text-to-Speech (Bytes)
 * 
 * POST /tts/bytes
 * 
 * Also accepts auth: AccessTokenAuth
 */
export const createApiTtsBytes = async (args: CreateApiTtsBytesArgs, options?: CreateApiTtsBytesOptions) => {
const {baseUrl = "https://api.cartesia.ai", fetch: fetchFn = fetch, APIKeyAuth} = options ?? {}

const query = new URLSearchParams()
const headers = new Headers()
headers.set('content-type', "application/json")
headers.set('accept', "audio/*")

if (args['Cartesia-Version'] != null) headers.set("Cartesia-Version", String(args['Cartesia-Version']))
if (APIKeyAuth !== undefined) headers.set('authorization', `Bearer ${APIKeyAuth}`)

const url = `${baseUrl.replace(/\/+$/, '')}/tts/bytes${query.size > 0 ? `?${query}` : ''}`

const res = await fetchFn(url, {method: "POST", headers, body: JSON.stringify(args.body)})

if (!res.ok) throw new Error(`Request failed with status ${res.status}`, {cause: {status: res.status, body: await res.text()}})

return res.blob()
};