API · Gemini 3.8 Flash-Lite TTS API：자연스러운 음성

google/gemini-3.8-flash-lite-tts/text-to-speech0.03크레딧부터 /초

2026년 9월 출시된 구글의 Gemini 3.8 Flash-Lite TTS는 3.8 Flash TTS보다 더 빠르고 저렴한 형제 모델입니다. 스크립트를 보내고 30가지 음성 중 하나를 선택하면 보통 몇 초 안에 WAV 파일을 받을 수 있습니다.

POST /jobs/createTask에서 모델 이름을 google/gemini-3.8-flash-lite-tts/text-to-speech(으)로 지정하면 호출할 수 있습니다. 0.03크레딧/초부터(US$0.0003). 새 계정에는 30크레딧이 지급되니 Playground에서 먼저 무료로 써 보세요.

텍스트 음성 변환
목소리 30종

GoogleAPI 키 받기 Gemini 3.8 Flash-Lite TTS 예시와 프롬프트 →

모델 이름google/gemini-3.8-flash-lite-tts/text-to-speech

엔드포인트POST 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": "google/gemini-3.8-flash-lite-tts/text-to-speech",
  "input": {
    "text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
    "voice_id": "Kore"
  }
}'

# 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": "google/gemini-3.8-flash-lite-tts/text-to-speech",
    "input": {
      "text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
      "voice_id": "Kore"
    }
  }),
});

// 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": "google/gemini-3.8-flash-lite-tts/text-to-speech",
        "input": {
            "text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
            "voice_id": "Kore"
        }
    },
)["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"])

input은 아래 스키마로 만들었기 때문에 그대로 검증을 통과합니다. 프롬프트와 링크만 내 것으로 바꾸세요.

가격

옵션	크레딧 /초	≈ USD
기본	0.03	US$0.0003

1크레딧 = $0.01 · 모든 옵션과 가격: GET /models/google/gemini-3.8-flash-lite-tts/text-to-speech

제한

텍스트 길이(글자): 5,000
목소리: 30

파라미터

이 필드들은 모든 요청을 검사할 때 쓰는 것과 같은 스키마에서 나옵니다. 목록에 없는 필드는 거부됩니다.

일부 필드는 서로 연결되어 있습니다(예: 참조 자료가 최소 하나 필요). 정확한 규칙은 아래 원본 스키마에 있습니다.

textstring경우에 따라 필수
The words to be spoken, exactly as written. Spell out sounds such as sighs or laughter; bracketed cues may be read aloud.
범위
1 – 5000 chars
dialoguearray<object>경우에 따라 필수
A scripted conversation, used instead of text: each line names a speaker from speakers.
범위
1 – 20 items
내부 필드
- dialogue[].textstring필수
  The line, exactly as it should be spoken.
  범위
  1 – 250 chars
- dialogue[].speakerstring필수
  A name from speakers.
  범위
  1 – 40 chars
speakersarray<object>경우에 따라 필수
The cast for dialogue: one or two voices, each with a name the lines refer to.
범위
1 – 2 items
내부 필드
- speakers[].namestring필수
  Name the dialogue lines use for this speaker.
  범위
  1 – 40 chars
- speakers[].voice_idstring필수
  Prebuilt voice for this speaker.
  허용 값
  "Achernar""Achird""Algenib""Algieba""Alnilam""Aoede""Autonoe""Callirrhoe""Charon""Despina""Enceladus""Erinome""Fenrir""Gacrux""Iapetus""Kore""Laomedeia""Leda""Orus""Puck""Pulcherrima""Rasalgethi""Sadachbia""Sadaltager""Schedar""Sulafat""Umbriel""Vindemiatrix""Zephyr""Zubenelgenubi"
- speakers[].pacestring선택
  Rhythm of this speaker's lines.
  허용 값
  "natural""rapid_fire""the_drift""staccato"
- speakers[].stylestring선택
  Manner of this speaker's lines.
  허용 값
  "whisper""empathetic""vocal_smile""newscaster""promo_hype""deadpan"
- speakers[].accentstring선택
  English accent for this speaker.
  허용 값
  "neutral""american_general""american_valley""american_south""british_rp""british_brixton""transatlantic""australian"
- speakers[].profilestring선택
  Short description of who is speaking; not read aloud.
  범위
  0 – 300 chars
voice_idstring선택
사용 가능한 목소리 중에서 고릅니다.
기본값
"Kore"
허용 값
"Achernar""Achird""Algenib""Algieba""Alnilam""Aoede""Autonoe""Callirrhoe""Charon""Despina""Enceladus""Erinome""Fenrir""Gacrux""Iapetus""Kore""Laomedeia""Leda""Orus""Puck""Pulcherrima""Rasalgethi""Sadachbia""Sadaltager""Schedar""Sulafat""Umbriel""Vindemiatrix""Zephyr""Zubenelgenubi"
stylestring선택
미리 준비된 스타일이나 장르.
허용 값
"whisper""empathetic""vocal_smile""newscaster""promo_hype""deadpan"
pacestring선택
Rhythm of the reading. Omit it to keep the voice's own rhythm.
허용 값
"natural""rapid_fire""the_drift""staccato"
accentstring선택
English accent used for the reading.
허용 값
"neutral""american_general""american_valley""american_south""british_rp""british_brixton""transatlantic""australian"
instructionsstring선택
How to read the text: mood, distance from the microphone, who is listening. Shapes the delivery and is not spoken.
범위
0 – 1000 chars
scenestring선택
Where and to whom the words are spoken. Shapes the delivery and is not spoken.
범위
0 – 500 chars
temperaturenumber선택
Variation between takes; higher is less predictable.
범위
0 – 2

원본 JSON 스키마

{
  "type": "object",
  "allOf": [
    {
      "if": {
        "required": [
          "dialogue"
        ]
      },
      "then": {
        "required": [
          "speakers"
        ]
      }
    }
  ],
  "anyOf": [
    {
      "required": [
        "text"
      ]
    },
    {
      "required": [
        "dialogue"
      ]
    }
  ],
  "required": [],
  "properties": {
    "pace": {
      "enum": [
        "natural",
        "rapid_fire",
        "the_drift",
        "staccato"
      ],
      "type": "string",
      "description": "Rhythm of the reading. Omit it to keep the voice's own rhythm."
    },
    "text": {
      "type": "string",
      "maxLength": 5000,
      "minLength": 1,
      "description": "The words to be spoken, exactly as written. Spell out sounds such as sighs or laughter; bracketed cues may be read aloud."
    },
    "scene": {
      "type": "string",
      "maxLength": 500,
      "description": "Where and to whom the words are spoken. Shapes the delivery and is not spoken."
    },
    "style": {
      "enum": [
        "whisper",
        "empathetic",
        "vocal_smile",
        "newscaster",
        "promo_hype",
        "deadpan"
      ],
      "type": "string",
      "description": "Overall manner of the reading. Omit it to use the voice's own default manner."
    },
    "accent": {
      "enum": [
        "neutral",
        "american_general",
        "american_valley",
        "american_south",
        "british_rp",
        "british_brixton",
        "transatlantic",
        "australian"
      ],
      "type": "string",
      "description": "English accent used for the reading."
    },
    "dialogue": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "speaker",
          "text"
        ],
        "properties": {
          "text": {
            "type": "string",
            "maxLength": 250,
            "minLength": 1,
            "description": "The line, exactly as it should be spoken."
          },
          "speaker": {
            "type": "string",
            "maxLength": 40,
            "minLength": 1,
            "description": "A name from speakers."
          }
        },
        "additionalProperties": false
      },
      "maxItems": 20,
      "minItems": 1,
      "description": "A scripted conversation, used instead of text: each line names a speaker from speakers."
    },
    "speakers": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name",
          "voice_id"
        ],
        "properties": {
          "name": {
            "type": "string",
            "maxLength": 40,
            "minLength": 1,
            "description": "Name the dialogue lines use for this speaker."
          },
          "pace": {
            "enum": [
              "natural",
              "rapid_fire",
              "the_drift",
              "staccato"
            ],
            "type": "string",
            "description": "Rhythm of this speaker's lines."
          },
          "style": {
            "enum": [
              "whisper",
              "empathetic",
              "vocal_smile",
              "newscaster",
              "promo_hype",
              "deadpan"
            ],
            "type": "string",
            "description": "Manner of this speaker's lines."
          },
          "accent": {
            "enum": [
              "neutral",
              "american_general",
              "american_valley",
              "american_south",
              "british_rp",
              "british_brixton",
              "transatlantic",
              "australian"
            ],
            "type": "string",
            "description": "English accent for this speaker."
          },
          "profile": {
            "type": "string",
            "maxLength": 300,
            "description": "Short description of who is speaking; not read aloud."
          },
          "voice_id": {
            "enum": [
              "Achernar",
              "Achird",
              "Algenib",
              "Algieba",
              "Alnilam",
              "Aoede",
              "Autonoe",
              "Callirrhoe",
              "Charon",
              "Despina",
              "Enceladus",
              "Erinome",
              "Fenrir",
              "Gacrux",
              "Iapetus",
              "Kore",
              "Laomedeia",
              "Leda",
              "Orus",
              "Puck",
              "Pulcherrima",
              "Rasalgethi",
              "Sadachbia",
              "Sadaltager",
              "Schedar",
              "Sulafat",
              "Umbriel",
              "Vindemiatrix",
              "Zephyr",
              "Zubenelgenubi"
            ],
            "type": "string",
            "description": "Prebuilt voice for this speaker."
          }
        },
        "additionalProperties": false
      },
      "maxItems": 2,
      "minItems": 1,
      "description": "The cast for dialogue: one or two voices, each with a name the lines refer to."
    },
    "voice_id": {
      "enum": [
        "Achernar",
        "Achird",
        "Algenib",
        "Algieba",
        "Alnilam",
        "Aoede",
        "Autonoe",
        "Callirrhoe",
        "Charon",
        "Despina",
        "Enceladus",
        "Erinome",
        "Fenrir",
        "Gacrux",
        "Iapetus",
        "Kore",
        "Laomedeia",
        "Leda",
        "Orus",
        "Puck",
        "Pulcherrima",
        "Rasalgethi",
        "Sadachbia",
        "Sadaltager",
        "Schedar",
        "Sulafat",
        "Umbriel",
        "Vindemiatrix",
        "Zephyr",
        "Zubenelgenubi"
      ],
      "type": "string",
      "default": "Kore",
      "description": "Prebuilt voice that reads the text. Each voice has a fixed character."
    },
    "temperature": {
      "type": "number",
      "maximum": 2,
      "minimum": 0,
      "description": "Variation between takes; higher is less predictable."
    },
    "instructions": {
      "type": "string",
      "maxLength": 1000,
      "description": "How to read the text: mood, distance from the microphone, who is listening. Shapes the delivery and is not spoken."
    }
  },
  "additionalProperties": false
}

응답, 폴링, 콜백

모든 모델은 같은 방식으로 동작합니다. 작업을 만들고, 폴링하거나 콜백을 기다리세요.

먼저 견적 받기

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": "google/gemini-3.8-flash-lite-tts/text-to-speech",
  "input": {
    "text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
    "voice_id": "Kore"
  }
}'

본문은 createTask와 같습니다. 예상 청구액과 최대 청구액을 돌려주며, 아무것도 실행하지 않습니다.

접수됨

HTTP

HTTP/1.1 202 Accepted

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

HTTP 202는 작업이 접수되었고 크레딧이 보류만 되었을 뿐 아직 차감되지 않았다는 뜻입니다. 최종 청구액은 보류액을 넘지 않습니다.

상태 확인

cURL

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

간격을 조금씩 늘리며 몇 초마다 확인하고, state가 succeeded, failed, canceled, expired 중 하나가 되면 멈추세요.

완료된 작업

JSON

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
    "model": "google/gemini-3.8-flash-lite-tts/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"
}

expiresAt 전에 url에서 내려받으세요. 나중에 새 링크가 필요하면 POST /common/download-url을 호출하세요.

콜백 검증하기

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
});

callBackUrl을 설정하면 완료된 작업을 보내 드립니다. 믿기 전에 원본 요청 본문으로 서명을 확인하세요.

로컬 파일 보내기

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.

공개 https 링크는 그대로 쓸 수 있습니다. 로컬 파일은 먼저 upload-url과 commit을 거칩니다.