Google AI (Gemini API)음성 합성AI generation

Google: Gemini 3.8 Flash TTS

google-ai.voice-gen.gemini-3-8-flash-tts

Speak a text in one of 30 prebuilt voices, or a two-speaker dialogue, with Gemini 3.8 Flash TTS on Google's own API; the audio returns inline as base64 WAV (24 kHz mono).

가격: $0.05/success정가 기준
성공률: 99.9%최근 30일 · 45,570회
지연 시간 p50: 3 sp95 12 s
마지막 검증: 2026. 9. 30.동작 확인됨

POSThttps://toolswitch.dev/v1/tools/google-ai.voice-gen.gemini-3-8-flash-ttsBeta

온라인에서 사용해 보기공급자 문서 ↗

플랫폼 할당량 사용
동기 응답
공개 데이터 읽기

파라미터

파라미터	유형	필수	설명	예시
경로 파라미터
`model`	문자열	필수		`gemini-3.8-flash-tts`
요청 본문(JSON)
`contents`	배열	필수	One user turn: {parts: [{text: script}]}. Style is steered in the text itself ("Say cheerfully: ..."). For two speakers, give each line its own part with its speaker: [{text: "Did it finish?", speechMetadata: {speaker: Joe}}, {text: "Yes.", speechMetadata: {speaker: Jane}}], and name both in multiSpeakerVoiceConfig; a single "Joe: ... Jane: ..." text answers 400.	`[{"parts":[{"text":"Say cheerfully: Welcome to treg."}]}]`
`generationConfig`	객체	필수		`{"speechConfig":{"voiceConfig":{"prebuiltVoiceConfig":{"voiceName":"Kore"}}},"responseModalities":["AUDIO"]}`

경로 파라미터
model문자열필수
예시: gemini-3.8-flash-tts
요청 본문(JSON)
contents배열필수
One user turn: {parts: [{text: script}]}. Style is steered in the text itself ("Say cheerfully: ..."). For two speakers, give each line its own part with its speaker: [{text: "Did it finish?", speechMetadata: {speaker: Joe}}, {text: "Yes.", speechMetadata: {speaker: Jane}}], and name both in multiSpeakerVoiceConfig; a single "Joe: ... Jane: ..." text answers 400.
예시: [{"parts":[{"text":"Say cheerfully: Welcome to treg."}]}]
generationConfig객체필수
예시: {"speechConfig":{"voiceConfig":{"prebuiltVoiceConfig":{"voiceName":"Kore"}}},"responseModalities":["AUDIO"]}

코드 예제

$TOOLSWITCH_KEY를 콘솔에서 생성한 키로 바꾸세요.

Beta

curl -X POST 'https://toolswitch.dev/v1/tools/google-ai.voice-gen.gemini-3-8-flash-tts' \
  -H "X-Toolswitch-Key: $TOOLSWITCH_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{"contents":[{"parts":[{"text":"Say cheerfully: Welcome to treg, the tool catalog for your agents."}]}],"generationConfig":{"speechConfig":{"voiceConfig":{"prebuiltVoiceConfig":{"voiceName":"Kore"}}},"responseModalities":["AUDIO"]}}'

import os
import json
import requests

response = requests.request(
    "POST",
    "https://toolswitch.dev/v1/tools/google-ai.voice-gen.gemini-3-8-flash-tts",
    headers={"X-Toolswitch-Key": os.environ["TOOLSWITCH_KEY"]},
    json=json.loads("{\"contents\":[{\"parts\":[{\"text\":\"Say cheerfully: Welcome to treg, the tool catalog for your agents.\"}]}],\"generationConfig\":{\"speechConfig\":{\"voiceConfig\":{\"prebuiltVoiceConfig\":{\"voiceName\":\"Kore\"}}},\"responseModalities\":[\"AUDIO\"]}}"),
)
response.raise_for_status()
print(response.text)

const response = await fetch("https://toolswitch.dev/v1/tools/google-ai.voice-gen.gemini-3-8-flash-tts", {
  method: "POST",
  headers: {
    "X-Toolswitch-Key": process.env.TOOLSWITCH_KEY ?? "",
    "Content-Type": "application/json",
  },
  body: JSON.stringify(JSON.parse("{\"contents\":[{\"parts\":[{\"text\":\"Say cheerfully: Welcome to treg, the tool catalog for your agents.\"}]}],\"generationConfig\":{\"speechConfig\":{\"voiceConfig\":{\"prebuiltVoiceConfig\":{\"voiceName\":\"Kore\"}}},\"responseModalities\":[\"AUDIO\"]}}")),
});
if (!response.ok) throw new Error(`Request failed: ${response.status}`);
console.log(await response.text());

게이트웨이 API는 Beta이며 URL과 인증 방식이 변경될 수 있습니다. 예제 매개변수는 샘플 데이터입니다. 호출 요금은 $0.05/success이며 서비스 수수료가 포함되어 있습니다.