API · MiniMax Speech 2.8 Turbo — TTS, 472 голоса

от MiniMax

Быстрая речь, 400+ голосов и управление эмоциями

minimax/speech-2.8-turbo/text-to-speechОт 11 кредитовза 1000 символов · 0,11 $

Попробовать в Playground Получить API-ключ

Голосов: 472
Языков: 40
Озвучка текста

Вызывайте его по имени модели minimax/speech-2.8-turbo/text-to-speech через POST /jobs/createTask, от 11 кредитов за 1000 символов (0,11 $). Новые аккаунты получают 30 бесплатных кредитов, чтобы вы могли сначала попробовать в Playground.

Имя моделиminimax/speech-2.8-turbo/text-to-speech

ЭндпоинтPOST https://api.popnow.ai/api/v1/jobs/createTask

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "minimax/speech-2.8-turbo/text-to-speech",
  "input": {
    "text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
    "voice_id": "Calm_Woman",
    "emotion": "neutral",
    "language": "auto",
    "output_format": "mp3"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

// Node 18+ (or any runtime with fetch). Keep the API key on your server.
const BASE = "https://api.popnow.ai/api/v1";
const headers = { Authorization: `Bearer ${process.env.POPNOW_API_KEY}` };
const sleep = (ms) => new Promise((r) => setTimeout(r, ms));

async function call(path, init = {}) {
  const res = await fetch(BASE + path, { ...init, headers: { ...headers, ...init.headers } });
  const body = await res.json();
  if (body.code !== 200) throw new Error(`${body.code} ${body.msg}`);
  return body.data;
}

const { taskId } = await call("/jobs/createTask", {
  method: "POST",
  headers: { "Content-Type": "application/json", "Idempotency-Key": crypto.randomUUID() },
  body: JSON.stringify({
    "model": "minimax/speech-2.8-turbo/text-to-speech",
    "input": {
      "text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
      "voice_id": "Calm_Woman",
      "emotion": "neutral",
      "language": "auto",
      "output_format": "mp3"
    }
  }),
});

// Poll with backoff. A finished task may still be copying files: wait while an asset is pending.
let task;
for (let delay = 2000; ; delay = Math.min(delay * 1.5, 15000)) {
  await sleep(delay);
  task = await call(`/jobs/recordInfo?taskId=${taskId}`);
  const copying = (task.output?.assets ?? []).some((a) => a.pending && !a.unavailable);
  if (["succeeded", "failed", "canceled", "expired"].includes(task.state) && !copying) break;
}
if (task.state !== "succeeded") throw new Error(`${task.state}: ${task.errorMessage ?? "no detail"}`);

// Each asset has a signed url (no API key needed) that expires at expiresAt: save the file.
for (const asset of task.output.assets) console.log(asset.url);

import os, time, uuid, requests

BASE = "https://api.popnow.ai/api/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['POPNOW_API_KEY']}"}


def call(method, path, **kwargs):
    body = requests.request(method, BASE + path, headers={**HEADERS, **kwargs.pop("headers", {})}, timeout=30, **kwargs).json()
    if body["code"] != 200:
        raise RuntimeError(f'{body["code"]} {body["msg"]}')
    return body["data"]


task_id = call(
    "POST",
    "/jobs/createTask",
    headers={"Idempotency-Key": str(uuid.uuid4())},  # reuse it if you retry
    json={
        "model": "minimax/speech-2.8-turbo/text-to-speech",
        "input": {
            "text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
            "voice_id": "Calm_Woman",
            "emotion": "neutral",
            "language": "auto",
            "output_format": "mp3"
        }
    },
)["taskId"]

# Poll with backoff. A finished task may still be copying files: wait while an asset is pending.
delay = 2.0
while True:
    time.sleep(delay)
    task = call("GET", "/jobs/recordInfo", params={"taskId": task_id})
    assets = (task.get("output") or {}).get("assets") or []
    copying = any(a.get("pending") and not a.get("unavailable") for a in assets)
    if task["state"] in ("succeeded", "failed", "canceled", "expired") and not copying:
        break
    delay = min(delay * 1.5, 15.0)

if task["state"] != "succeeded":
    raise RuntimeError(f'{task["state"]}: {task.get("errorMessage", "no detail")}')

# Each asset has a signed url (no API key needed) that expires at expiresAt: save the file.
for asset in assets:
    print(asset["url"])

input собран по схеме ниже, поэтому проходит проверку как есть. Замените промпт и ссылки на свои.

Цена

Вариант	Кредиты за 1000 символов	≈ USD
Стандарт	10,8	0,11 $

1 кредит = 0,01 $ · Все варианты и цены: GET /models/minimax/speech-2.8-turbo/text-to-speech

Каждая задача округляется вверх до целых кредитов, поэтому один запуск на самом дешёвом уровне стоит 11 кредитов за 1000 символов (0,11 $).

Ограничения

Длина текста (символов): 5,000
Голоса: 473
Языки: 40

Параметры

Эти поля взяты из той же схемы, по которой мы проверяем каждый запрос. Поля, которых нет в списке, отклоняются.

textstringОбязательное
The words to be spoken, exactly as written. Sound tags such as (sighs) or (laughs) are performed. Billed per 1,000 characters.
Диапазон
1 – 5000 chars
voice_idstringНеобязательное
Выберите один из доступных голосов.
По умолчанию
"Calm_Woman"
Допустимые значения
"Wise_Woman""Friendly_Person""Inspirational_girl""Deep_Voice_Man""Calm_Woman""Casual_Guy""Lively_Girl""Patient_Man""Young_Knight""Determined_Man""Lovely_Girl""Decent_Boy""Imposing_Manner""Elegant_Man""Abbess""Sweet_Girl_2""Exuberant_Girl""English_expressive_narrator""English_radiant_girl""English_magnetic_voiced_man""English_compelling_lady1""English_Aussie_Bloke""English_captivating_female1""English_Upbeat_Woman""English_Trustworth_Man""English_CalmWoman""English_UpsetGirl""English_Gentle-voiced_man""English_Whispering_girl_v3""English_Diligent_Man""English_Graceful_Lady""English_Husky_MetalHead""English_ReservedYoungMan""English_PlayfulGirl""English_ManWithDeepVoice""English_GentleTeacher""English_MaturePartner""English_FriendlyPerson""English_MatureBoss""English_Debator"+433
emotionstringНеобязательное
Эмоция в голосе.
По умолчанию
"neutral"
Допустимые значения
"neutral""happy""sad""angry""fearful""disgusted""surprised"
speednumberНеобязательное
Темп речи.
По умолчанию
1
Диапазон
0.5 – 2
pitchintegerНеобязательное
Pitch shift in semitones; 0 keeps the voice's own pitch.
По умолчанию
0
Диапазон
-12 – 12
volumenumberНеобязательное
Loudness multiplier; 1 is the normal level.
По умолчанию
1
Диапазон
0.1 – 10
languagestringНеобязательное
Язык озвучки.
По умолчанию
"auto"
Допустимые значения
"auto""zh""yue""en""ar""ru""es""fr""pt""de""tr""nl""uk""vi""id""ja""it""ko""th""pl""ro""el""cs""fi""hi""bg""da""he""ms""fa""sk""sv""hr""fil""hu""no""sl""ca""nn""ta"+1
output_formatstringНеобязательное
Формат файла результата.
По умолчанию
"mp3"
Допустимые значения
"mp3""wav""flac""pcm"
sample_rateintegerНеобязательное
Sample rate in Hz. The model uses 32000 when omitted.
Допустимые значения
80001600022050240003200044100
bitrateintegerНеобязательное
MP3 bitrate in bits per second; ignored for other formats. The model uses 128000 when omitted.
Допустимые значения
3200064000128000256000
audio_channelsstringНеобязательное
Mono or stereo output. Mono when omitted.
Допустимые значения
"mono""stereo"
english_normalizationbooleanНеобязательное
Read numbers, dates and abbreviations in English text the way a person would say them.
По умолчанию
false
pronunciation_dictarray<object>Необязательное
Custom pronunciations: each alias in the text is read as its pronunciation.
Диапазон
0 – 100 items
Вложенные поля
- pronunciation_dict[].aliasstringОбязательное
  The text as written in the script, without slashes.
  Диапазон
  1 – 100 chars
- pronunciation_dict[].pronunciationstringОбязательное
  How to read it: plain words or IPA in parentheses.
  Диапазон
  1 – 200 chars

Исходная JSON-схема

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 5000,
      "minLength": 1,
      "description": "The words to be spoken, exactly as written. Sound tags such as (sighs) or (laughs) are performed. Billed per 1,000 characters."
    },
    "pitch": {
      "type": "integer",
      "default": 0,
      "maximum": 12,
      "minimum": -12,
      "description": "Pitch shift in semitones; 0 keeps the voice's own pitch."
    },
    "speed": {
      "type": "number",
      "default": 1,
      "maximum": 2,
      "minimum": 0.5,
      "description": "Speaking rate; 1 is the voice's normal pace."
    },
    "volume": {
      "type": "number",
      "default": 1,
      "maximum": 10,
      "minimum": 0.1,
      "description": "Loudness multiplier; 1 is the normal level."
    },
    "bitrate": {
      "enum": [
        32000,
        64000,
        128000,
        256000
      ],
      "type": "integer",
      "description": "MP3 bitrate in bits per second; ignored for other formats. The model uses 128000 when omitted."
    },
    "emotion": {
      "enum": [
        "neutral",
        "happy",
        "sad",
        "angry",
        "fearful",
        "disgusted",
        "surprised"
      ],
      "type": "string",
      "default": "neutral",
      "description": "Emotion of the reading."
    },
    "language": {
      "enum": [
        "auto",
        "zh",
        "yue",
        "en",
        "ar",
        "ru",
        "es",
        "fr",
        "pt",
        "de",
        "tr",
        "nl",
        "uk",
        "vi",
        "id",
        "ja",
        "it",
        "ko",
        "th",
        "pl",
        "ro",
        "el",
        "cs",
        "fi",
        "hi",
        "bg",
        "da",
        "he",
        "ms",
        "fa",
        "sk",
        "sv",
        "hr",
        "fil",
        "hu",
        "no",
        "sl",
        "ca",
        "nn",
        "ta",
        "af"
      ],
      "type": "string",
      "default": "auto",
      "description": "Language hint that improves pronunciation; auto detects it from the text."
    },
    "voice_id": {
      "enum": [
        "Wise_Woman",
        "Friendly_Person",
        "Inspirational_girl",
        "Deep_Voice_Man",
        "Calm_Woman",
        "Casual_Guy",
        "Lively_Girl",
        "Patient_Man",
        "Young_Knight",
        "Determined_Man",
        "Lovely_Girl",
        "Decent_Boy",
        "Imposing_Manner",
        "Elegant_Man",
        "Abbess",
        "Sweet_Girl_2",
        "Exuberant_Girl",
        "English_expressive_narrator",
        "English_radiant_girl",
        "English_magnetic_voiced_man",
        "English_compelling_lady1",
        "English_Aussie_Bloke",
        "English_captivating_female1",
        "English_Upbeat_Woman",
        "English_Trustworth_Man",
        "English_CalmWoman",
        "English_UpsetGirl",
        "English_Gentle-voiced_man",
        "English_Whispering_girl_v3",
        "English_Diligent_Man",
        "English_Graceful_Lady",
        "English_Husky_MetalHead",
        "English_ReservedYoungMan",
        "English_PlayfulGirl",
        "English_ManWithDeepVoice",
        "English_GentleTeacher",
        "English_MaturePartner",
        "English_FriendlyPerson",
        "English_MatureBoss",
        "English_Debator",
        "whisper_man",
        "English_Abbess",
        "English_LovelyGirl",
        "whisper_woman_1",
        "English_Steadymentor",
        "English_Deep-VoicedGentleman",
        "English_DeterminedMan",
        "English_Wiselady",
        "English_CaptivatingStoryteller",
        "English_AttractiveGirl",
        "English_DecentYoungMan",
        "English_SentimentalLady",
        "English_ImposingManner",
        "English_SadTeen",
        "English_ThoughtfulMan",
        "English_PassionateWarrior",
        "English_DecentBoy",
        "English_WiseScholar",
        "English_Soft-spokenGirl",
        "English_SereneWoman",
        "English_ConfidentWoman",
        "English_PatientMan",
        "English_Comedian",
        "English_GorgeousLady",
        "English_BossyLeader",
        "English_LovelyLady",
        "English_Strong-WilledBoy",
        "English_Deep-tonedMan",
        "English_StressedLady",
        "English_AssertiveQueen",
        "English_AnimeCharacter",
        "English_Jovialman",
        "English_WhimsicalGirl",
        "English_CharmingQueen",
        "English_Kind-heartedGirl",
        "English_FriendlyNeighbor",
        "English_Sweet_Female_4",
        "English_Magnetic_Male_2",
        "English_Lively_Male_11",
        "English_Friendly_Female_3",
        "English_Steady_Female_1",
        "English_Lively_Male_10",
        "English_Magnetic_Male_12",
        "English_Steady_Female_5",
        "English_Insightful_Speaker",
        "English_patient_man_v1",
        "English_Persuasive_Man",
        "English_Explanatory_Man",
        "English_intellect_female_1",
        "English_energetic_male_1",
        "English_witty_female_1",
        "English_Lucky_Robot",
        "English_Cute_Girl",
        "English_Sharp_Commentator",
        "English_Honest_Man",
        "angry_pirate_1",
        "massive_kind_troll",
        "movie_trailer_deep",
        "peace_and_ease",
        "moss_audio_6dc281eb-713c-11f0-a447-9613c873494c",
        "moss_audio_c12a59b9-7115-11f0-a447-9613c873494c",
        "moss_audio_076697ad-7144-11f0-a447-9613c873494c",
        "moss_audio_737a299c-734a-11f0-918f-4e0486034804",
        "moss_audio_19dbb103-7350-11f0-ad20-f2bc95e89150",
        "moss_audio_7c7e7ae2-7356-11f0-9540-7ef9b4b62566",
        "moss_audio_570551b1-735c-11f0-b236-0adeeecad052",
        "moss_audio_ad5baf92-735f-11f0-8263-fe5a2fe98ec8",
        "moss_audio_cedfd4d2-736d-11f0-99be-fe40dd2a5fe8",
        "moss_audio_a0d611da-737c-11f0-ad20-f2bc95e89150",
        "moss_audio_4f4172f4-737b-11f0-9540-7ef9b4b62566",
        "moss_audio_62ca20b0-7380-11f0-99be-fe40dd2a5fe8",
        "conversational_female_1_v1",
        "conversational_female_2_v1",
        "socialmedia_female_1_v1",
        "BritishChild_male_1_v1",
        "BritishChild_female_1_v1",
        "Chinese (Mandarin)_Reliable_Executive",
        "Chinese (Mandarin)_News_Anchor",
        "Chinese (Mandarin)_Unrestrained_Young_Man",
        "Chinese (Mandarin)_Mature_Woman",
        "Arrogant_Miss",
        "Chinese (Mandarin)_Kind-hearted_Antie",
        "Robot_Armor",
        "hunyin_6",
        "Chinese (Mandarin)_HK_Flight_Attendant",
        "Chinese (Mandarin)_Humorous_Elder",
        "Chinese (Mandarin)_Gentleman",
        "Chinese (Mandarin)_Warm_Bestie",
        "Chinese (Mandarin)_Stubborn_Friend",
        "Chinese (Mandarin)_Sweet_Lady",
        "Chinese (Mandarin)_Southern_Young_Man",
        "Chinese (Mandarin)_Wise_Women",
        "Chinese (Mandarin)_Gentle_Youth",
        "Chinese (Mandarin)_Warm_Girl",
        "Chinese (Mandarin)_Male_Announcer",
        "Chinese (Mandarin)_Kind-hearted_Elder",
        "Chinese (Mandarin)_Cute_Spirit",
        "Chinese (Mandarin)_Radio_Host",
        "Chinese (Mandarin)_Lyrical_Voice",
        "Chinese (Mandarin)_Straightforward_Boy",
        "Chinese (Mandarin)_Sincere_Adult",
        "Chinese (Mandarin)_Gentle_Senior",
        "Chinese (Mandarin)_Crisp_Girl",
        "Chinese (Mandarin)_Pure-hearted_Boy",
        "Chinese (Mandarin)_Soft_Girl",
        "Chinese (Mandarin)_IntellectualGirl",
        "Chinese (Mandarin)_Warm_HeartedGirl",
        "Chinese (Mandarin)_Laid_BackGirl",
        "Chinese (Mandarin)_ExplorativeGirl",
        "Chinese (Mandarin)_Warm-HeartedAunt",
        "Chinese (Mandarin)_BashfulGirl",
        "Arabic_CalmWoman",
        "Arabic_FriendlyGuy",
        "Cantonese_ProfessionalHost(F)",
        "Cantonese_GentleLady",
        "Cantonese_ProfessionalHost(M)",
        "Cantonese_PlayfulMan",
        "Cantonese_CuteGirl",
        "Cantonese_KindWoman",
        "Cantonese_Narrator",
        "Cantonese_WiselProfessor",
        "Cantonese_IndifferentStaff",
        "Dutch_kindhearted_girl",
        "Dutch_bossy_leader",
        "French_Male_Speech_New",
        "French_Female_News Anchor",
        "French_CasualMan",
        "French_MovieLeadFemale",
        "French_FemaleAnchor",
        "French_MaleNarrator",
        "French_Female Journalist",
        "French_Female_Speech_New",
        "German_FriendlyMan",
        "German_SweetLady",
        "German_PlayfulMan",
        "Indonesian_SweetGirl",
        "Indonesian_ReservedYoungMan",
        "Indonesian_CharmingGirl",
        "Indonesian_CalmWoman",
        "Indonesian_ConfidentWoman",
        "Indonesian_CaringMan",
        "Indonesian_BossyLeader",
        "Indonesian_DeterminedBoy",
        "Indonesian_GentleGirl",
        "Italian_BraveHeroine",
        "Italian_Narrator",
        "Italian_WanderingSorcerer",
        "Italian_DiligentLeader",
        "Italian_ReliableMan",
        "Italian_AthleticStudent",
        "Italian_ArrogantPrincess",
        "Japanese_Whisper_Belle",
        "Japanese_IntellectualSenior",
        "Japanese_DecisivePrincess",
        "Japanese_LoyalKnight",
        "Japanese_DominantMan",
        "Japanese_SeriousCommander",
        "Japanese_ColdQueen",
        "Japanese_DependableWoman",
        "Japanese_GentleButler",
        "Japanese_KindLady",
        "Japanese_CalmLady",
        "Japanese_OptimisticYouth",
        "Japanese_GenerousIzakayaOwner",
        "Japanese_SportyStudent",
        "Japanese_InnocentBoy",
        "Japanese_GracefulMaiden",
        "Korean_PowerfulGirl",
        "Korean_BossyMan",
        "Korean_SweetGirl",
        "Korean_CheerfulBoyfriend",
        "Korean_EnchantingSister",
        "Korean_ShyGirl",
        "Korean_ReliableSister",
        "Korean_StrictBoss",
        "Korean_SassyGirl",
        "Korean_ChildhoodFriendGirl",
        "Korean_PlayboyCharmer",
        "Korean_ElegantPrincess",
        "Korean_BraveFemaleWarrior",
        "Korean_BraveYouth",
        "Korean_CalmLady",
        "Korean_EnthusiasticTeen",
        "Korean_SoothingLady",
        "Korean_IntellectualSenior",
        "Korean_LonelyWarrior",
        "Korean_MatureLady",
        "Korean_InnocentBoy",
        "Korean_CharmingSister",
        "Korean_AthleticStudent",
        "Korean_BraveAdventurer",
        "Korean_CalmGentleman",
        "Korean_WiseElf",
        "Korean_CheerfulCoolJunior",
        "Korean_DecisiveQueen",
        "Korean_ColdYoungMan",
        "Korean_MysteriousGirl",
        "Korean_QuirkyGirl",
        "Korean_ConsiderateSenior",
        "Korean_CheerfulLittleSister",
        "Korean_DominantMan",
        "Korean_AirheadedGirl",
        "Korean_ReliableYouth",
        "Korean_FriendlyBigSister",
        "Korean_GentleBoss",
        "Korean_ColdGirl",
        "Korean_HaughtyLady",
        "Korean_CharmingElderSister",
        "Korean_IntellectualMan",
        "Korean_CaringWoman",
        "Korean_WiseTeacher",
        "Korean_ConfidentBoss",
        "Korean_AthleticGirl",
        "Korean_PossessiveMan",
        "Korean_GentleWoman",
        "Korean_CockyGuy",
        "Korean_ThoughtfulWoman",
        "Korean_OptimisticYouth",
        "Portuguese_AnxiousMan",
        "Portuguese_Matureresearcher",
        "Portuguese_Optimisticyouth",
        "Portuguese_CuteElf",
        "Portuguese_EnergeticGirl",
        "Portuguese_FunnyGuy",
        "Portuguese_Nuttylady",
        "Portuguese_Deep-tonedMan",
        "Portuguese_SentimentalLady",
        "Portuguese_BossyLeader",
        "Portuguese_Wiselady",
        "Portuguese_Strong-WilledBoy",
        "Portuguese_Deep-VoicedGentleman",
        "Portuguese_UpsetGirl",
        "Portuguese_PassionateWarrior",
        "Portuguese_AnimeCharacter",
        "Portuguese_ConfidentWoman",
        "Portuguese_AngryMan",
        "Portuguese_CaptivatingStoryteller",
        "Portuguese_Godfather",
        "Portuguese_ReservedYoungMan",
        "Portuguese_SmartYoungGirl",
        "Portuguese_Kind-heartedGirl",
        "Portuguese_Pompouslady",
        "Portuguese_Grinch",
        "Portuguese_Debator",
        "Portuguese_SweetGirl",
        "Portuguese_AttractiveGirl",
        "Portuguese_ThoughtfulMan",
        "Portuguese_PlayfulGirl",
        "Portuguese_GorgeousLady",
        "Portuguese_LovelyLady",
        "Portuguese_SereneWoman",
        "Portuguese_SadTeen",
        "Portuguese_MaturePartner",
        "Portuguese_Comedian",
        "Portuguese_NaughtySchoolgirl",
        "Portuguese_Narrator",
        "Portuguese_ToughBoss",
        "Portuguese_Fussyhostess",
        "Portuguese_Dramatist",
        "Portuguese_Steadymentor",
        "Portuguese_Jovialman",
        "Portuguese_CharmingQueen",
        "Portuguese_SantaClaus",
        "Portuguese_Rudolph",
        "Portuguese_Arnold",
        "Portuguese_CharmingSanta",
        "Portuguese_Ghost",
        "Portuguese_HumorousElder",
        "Portuguese_CalmLeader",
        "Portuguese_GentleTeacher",
        "Portuguese_EnergeticBoy",
        "Portuguese_ReliableMan",
        "Portuguese_SereneElder",
        "Portuguese_GrimReaper",
        "Portuguese_AssertiveQueen",
        "Portuguese_WhimsicalGirl",
        "Portuguese_StressedLady",
        "Portuguese_FriendlyNeighbor",
        "Portuguese_CaringGirlfriend",
        "Portuguese_PowerfulSoldier",
        "Portuguese_FascinatingBoy",
        "Portuguese_RomanticHusband",
        "Portuguese_StrictBoss",
        "Portuguese_InspiringLady",
        "Portuguese_PlayfulSpirit",
        "Portuguese_ElegantGirl",
        "Portuguese_CompellingGirl",
        "Portuguese_PowerfulVeteran",
        "Portuguese_SensibleManager",
        "Portuguese_ThoughtfulLady",
        "Portuguese_TheatricalActor",
        "Portuguese_FragileBoy",
        "Portuguese_ChattyGirl",
        "Portuguese_Conscientiousinstructor",
        "Portuguese_RationalMan",
        "Portuguese_WiseScholar",
        "Portuguese_FrankLady",
        "Portuguese_DeterminedManager",
        "Portuguese_CharmingLady",
        "Russian_HandsomeChildhoodFriend",
        "Russian_BrightHeroine",
        "Russian_AmbitiousWoman",
        "Russian_ReliableMan",
        "Russian_CrazyQueen",
        "Russian_PessimisticGirl",
        "Russian_AttractiveGuy",
        "Russian_Bad-temperedBoy",
        "Spanish_FriendlyNeighbor",
        "Spanish_FragileBoy",
        "Spanish_UpsetGirl",
        "Spanish_Soft-spokenGirl",
        "Spanish_CharmingQueen",
        "Spanish_Nuttylady",
        "Spanish_ElegantGirl",
        "Spanish_FascinatingBoy",
        "Spanish_FunnyGuy",
        "Spanish_PlayfulSpirit",
        "Spanish_TheatricalActor",
        "Spanish_SereneWoman",
        "Spanish_MaturePartner",
        "Spanish_CaptivatingStoryteller",
        "Spanish_Narrator",
        "Spanish_WiseScholar",
        "Spanish_Kind-heartedGirl",
        "Spanish_DeterminedManager",
        "Spanish_BossyLeader",
        "Spanish_ReservedYoungMan",
        "Spanish_ConfidentWoman",
        "Spanish_ThoughtfulMan",
        "Spanish_Strong-WilledBoy",
        "Spanish_SophisticatedLady",
        "Spanish_RationalMan",
        "Spanish_AnimeCharacter",
        "Spanish_Deep-tonedMan",
        "Spanish_Fussyhostess",
        "Spanish_SincereTeen",
        "Spanish_FrankLady",
        "Spanish_Comedian",
        "Spanish_Debator",
        "Spanish_ToughBoss",
        "Spanish_Wiselady",
        "Spanish_Steadymentor",
        "Spanish_Jovialman",
        "Spanish_SantaClaus",
        "Spanish_Rudolph",
        "Spanish_Intonategirl",
        "Spanish_Arnold",
        "Spanish_Ghost",
        "Spanish_HumorousElder",
        "Spanish_EnergeticBoy",
        "Spanish_WhimsicalGirl",
        "Spanish_StrictBoss",
        "Spanish_ReliableMan",
        "Spanish_SereneElder",
        "Spanish_AngryMan",
        "Spanish_AssertiveQueen",
        "Spanish_CaringGirlfriend",
        "Spanish_PowerfulSoldier",
        "Spanish_PassionateWarrior",
        "Spanish_ChattyGirl",
        "Spanish_RomanticHusband",
        "Spanish_CompellingGirl",
        "Spanish_PowerfulVeteran",
        "Spanish_SensibleManager",
        "Spanish_ThoughtfulLady",
        "Turkish_CalmWoman",
        "Turkish_Trustworthyman",
        "Ukrainian_CalmWoman",
        "Ukrainian_WiseScholar",
        "Vietnamese_Serene_Man",
        "Vietnamese_female_4_v1",
        "Vietnamese_male_1_v2",
        "Vietnamese_kindhearted_girl",
        "Thai_Optimistic_girl",
        "Thai_male_1_sample8",
        "Thai_Tender_Woman",
        "Thai_male_2_sample2",
        "Thai_female_1_sample1",
        "Thai_female_2_sample2",
        "Polish_male_1_sample4",
        "Polish_male_2_sample3",
        "Polish_female_1_sample1",
        "Polish_female_2_sample3",
        "Romanian_male_1_sample2",
        "Romanian_male_2_sample1",
        "Romanian_female_1_sample4",
        "Romanian_female_2_sample1",
        "Greek_female_1_sample1",
        "greek_male_1a_v1",
        "Greek_female_2_sample3",
        "czech_male_1_v1",
        "czech_female_5_v7",
        "czech_female_2_v2",
        "finnish_male_3_v1",
        "finnish_female_4_v1",
        "finnish_male_1_v2",
        "hindi_male_1_v2",
        "hindi_female_2_v1",
        "hindi_female_1_v2",
        "Bulgarian_male_2_v1",
        "Bulgarian_female_1_v1",
        "Danish_male_1_v1",
        "Danish_female_1_v1",
        "Hebrew_male_1_v1",
        "Hebrew_female_1_v1",
        "Malay_male_1_v1",
        "Malay_female_1_v1",
        "Malay_female_2_v1",
        "Persian_male_1_v1",
        "Persian_female_1_v1",
        "Slovak_male_1_v1",
        "Slovak_female_1_v1",
        "Swedish_male_1_v1",
        "Swedish_female_1_v1",
        "Croatian_male_1_v1",
        "Croatian_female_1_v1",
        "Filipino_male_1_v1",
        "Filipino_female_1_v1",
        "Hungarian_male_1_v1",
        "Hungarian_female_1_v1",
        "Norwegian_male_1_v1",
        "Norwegian_female_1_v1",
        "Slovenian_male_1_v1",
        "Slovenian_female_1_v2",
        "Catalan_male_1_v1",
        "Catalan_female_1_v1",
        "Nynorsk_male_1_v1",
        "Nynorsk_female_1_v1",
        "Tamil_male_1_v1",
        "Tamil_female_1_v1",
        "Afrikaans_male_1_v1",
        "Afrikaans_female_1_v1",
        "Chinese (Mandarin)_Sincere_Adult"
      ],
      "type": "string",
      "default": "Calm_Woman",
      "description": "System voice. The label shows the voice name and, where known, the language it is built for."
    },
    "sample_rate": {
      "enum": [
        8000,
        16000,
        22050,
        24000,
        32000,
        44100
      ],
      "type": "integer",
      "description": "Sample rate in Hz. The model uses 32000 when omitted."
    },
    "output_format": {
      "enum": [
        "mp3",
        "wav",
        "flac",
        "pcm"
      ],
      "type": "string",
      "default": "mp3",
      "description": "File format of the result; pcm is headerless 16-bit little-endian samples."
    },
    "audio_channels": {
      "enum": [
        "mono",
        "stereo"
      ],
      "type": "string",
      "description": "Mono or stereo output. Mono when omitted."
    },
    "pronunciation_dict": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "alias",
          "pronunciation"
        ],
        "properties": {
          "alias": {
            "type": "string",
            "pattern": "^[^/]+$",
            "maxLength": 100,
            "minLength": 1,
            "description": "The text as written in the script, without slashes."
          },
          "pronunciation": {
            "type": "string",
            "maxLength": 200,
            "minLength": 1,
            "description": "How to read it: plain words or IPA in parentheses."
          }
        },
        "additionalProperties": false
      },
      "maxItems": 100,
      "description": "Custom pronunciations: each alias in the text is read as its pronunciation."
    },
    "english_normalization": {
      "type": "boolean",
      "default": false,
      "description": "Read numbers, dates and abbreviations in English text the way a person would say them."
    }
  },
  "additionalProperties": false
}

Настоящий результат MiniMax Speech 2.8 Turbo

Промпт(laughs) Oh, you think you can keep up with me? Fine. Try. Just don't say I didn't warn you.

Тот же запрос через API

{
  "model": "minimax/speech-2.8-turbo/text-to-speech",
  "input": {
    "text": "(laughs) Oh, you think you can keep up with me? Fine. Try. Just don't say I didn't warn you.",
    "voice_id": "Lively_Girl",
    "emotion": "happy",
    "language": "auto",
    "output_format": "mp3"
  }
}

Ответы, опрос и колбэки

Все модели работают одинаково: создайте задачу, а затем опрашивайте её или дождитесь колбэка.

Сначала узнайте цену

cURL

curl -X POST https://api.popnow.ai/api/v1/jobs/quote \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/speech-2.8-turbo/text-to-speech",
  "input": {
    "text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
    "voice_id": "Calm_Woman",
    "emotion": "neutral",
    "language": "auto",
    "output_format": "mp3"
  }
}'

То же тело, что и у createTask. Возвращает ожидаемое и максимально возможное списание и ничего не запускает.

Принято

HTTP

HTTP/1.1 202 Accepted

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
    "state": "queued"
  },
  "request_id": "req_example_create"
}

HTTP 202 означает, что задача принята, а кредиты зарезервированы, но ещё не списаны. Итоговое списание никогда не превысит резерв.

Проверка статуса

cURL

curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Опрашивайте каждые несколько секунд, постепенно увеличивая паузу, и остановитесь, когда state станет succeeded, failed, canceled или expired.

Готовая задача

JSON

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
    "model": "minimax/speech-2.8-turbo/text-to-speech",
    "state": "succeeded",
    "output": {
      "assets": [
        {
          "url": "https://cdn.popnow.ai/tasks/task_01k3m8x9q2z4v7n5p6r8s0t1w3/output.mp3?signature=FROM_RESPONSE",
          "expiresAt": "2026-10-17T12:20:00Z",
          "mime": "audio/mpeg",
          "durationSeconds": 30
        }
      ]
    },
    "settled": true
  },
  "request_id": "req_example_record"
}

Скачайте файл по url до expiresAt. Нужна новая ссылка позже? Запросите её через POST /common/download-url.

Проверка колбэка

Node.js

import { createHash, createHmac, timingSafeEqual } from "node:crypto";
import express from "express";

const app = express();
// express.raw keeps the exact bytes that were signed; express.json would not match.
app.post("/hooks/popnow", express.raw({ type: "application/json" }), (req, res) => {
  const timestamp = req.header("X-Webhook-Timestamp");
  const signature = req.header("X-Webhook-Signature") ?? "";
  const body = JSON.parse(req.body.toString("utf8"));
  const taskId = body.data?.taskId ?? body.task_id;
  const digest = createHash("sha256").update(req.body).digest("hex");
  const expected = createHmac("sha256", process.env.POPNOW_WEBHOOK_SECRET)
    .update(`${taskId}.${timestamp}.${digest}`)
    .digest("base64");
  const ok = expected.length === signature.length && timingSafeEqual(Buffer.from(expected), Buffer.from(signature));
  // Check the signature first, then reject anything older than five minutes.
  if (!ok || Math.abs(Date.now() / 1000 - Number(timestamp)) > 300) return res.status(401).end();
  res.status(200).end(); // answer fast, then fetch the task and store its files
});

Если задан callBackUrl, мы пришлём вам готовую задачу. Прежде чем доверять ей, проверьте подпись по исходному телу запроса.

Отправка локального файла

cURL

curl -X POST https://api.popnow.ai/api/v1/common/upload-url \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contentType": "image/png", "bytes": 482113}'

# PUT the file bytes to data.uploadUrl with every header in data.headers, then commit it:
curl -X POST https://api.popnow.ai/api/v1/files/$FILE_ID/commit \
  -H "Authorization: Bearer $POPNOW_API_KEY"
# The commit returns a popnow://f/... reference. Put it in any image, video or
# audio field of the task input instead of a public https URL.

Публичные https-ссылки работают как есть. Локальные файлы сначала проходят через upload-url и commit.