Predict duration

Predict text-to-speech duration

curl --request POST \
  --url https://supertoneapi.com/v1/predict-duration/{voice_id} \
  --header 'Content-Type: application/json' \
  --header 'x-sup-api-key: <api-key>' \
  --data '
{
  "text": "<string>",
  "style": "<string>",
  "model": "sona_speech_1",
  "output_format": "wav",
  "voice_settings": {
    "pitch_shift": 0,
    "pitch_variance": 1,
    "speed": 1,
    "duration": 0,
    "similarity": 3,
    "text_guidance": 1,
    "subharmonic_amplitude_control": 1
  }
}
'

import requests

url = "https://supertoneapi.com/v1/predict-duration/{voice_id}"

payload = {
    "text": "<string>",
    "style": "<string>",
    "model": "sona_speech_1",
    "output_format": "wav",
    "voice_settings": {
        "pitch_shift": 0,
        "pitch_variance": 1,
        "speed": 1,
        "duration": 0,
        "similarity": 3,
        "text_guidance": 1,
        "subharmonic_amplitude_control": 1
    }
}
headers = {
    "x-sup-api-key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-sup-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    text: '<string>',
    style: '<string>',
    model: 'sona_speech_1',
    output_format: 'wav',
    voice_settings: {
      pitch_shift: 0,
      pitch_variance: 1,
      speed: 1,
      duration: 0,
      similarity: 3,
      text_guidance: 1,
      subharmonic_amplitude_control: 1
    }
  })
};

fetch('https://supertoneapi.com/v1/predict-duration/{voice_id}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://supertoneapi.com/v1/predict-duration/{voice_id}"

	payload := strings.NewReader("{\n  \"text\": \"<string>\",\n  \"style\": \"<string>\",\n  \"model\": \"sona_speech_1\",\n  \"output_format\": \"wav\",\n  \"voice_settings\": {\n    \"pitch_shift\": 0,\n    \"pitch_variance\": 1,\n    \"speed\": 1,\n    \"duration\": 0,\n    \"similarity\": 3,\n    \"text_guidance\": 1,\n    \"subharmonic_amplitude_control\": 1\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-sup-api-key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://supertoneapi.com/v1/predict-duration/{voice_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'text' => '<string>',
    'style' => '<string>',
    'model' => 'sona_speech_1',
    'output_format' => 'wav',
    'voice_settings' => [
        'pitch_shift' => 0,
        'pitch_variance' => 1,
        'speed' => 1,
        'duration' => 0,
        'similarity' => 3,
        'text_guidance' => 1,
        'subharmonic_amplitude_control' => 1
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-sup-api-key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

HttpResponse<String> response = Unirest.post("https://supertoneapi.com/v1/predict-duration/{voice_id}")
  .header("x-sup-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"text\": \"<string>\",\n  \"style\": \"<string>\",\n  \"model\": \"sona_speech_1\",\n  \"output_format\": \"wav\",\n  \"voice_settings\": {\n    \"pitch_shift\": 0,\n    \"pitch_variance\": 1,\n    \"speed\": 1,\n    \"duration\": 0,\n    \"similarity\": 3,\n    \"text_guidance\": 1,\n    \"subharmonic_amplitude_control\": 1\n  }\n}")
  .asString();

{
  "duration": 123
}

{
  "status": "error",
  "message": "Invalid request data"
}

{
  "status": "error",
  "message": {
    "message": "Invalid API Key",
    "error": "Unauthorized"
  }
}

{
  "status": "error",
  "message": {
    "message": "Not enough credits",
    "error": "Payment Required"
  }
}

{
  "status": "error",
  "message": {
    "message": "Permission denied",
    "error": "Forbidden"
  }
}

{
  "status": "error",
  "message": {
    "message": "Voice not found",
    "error": "Not Found"
  }
}

{
  "status": "error",
  "message": {
    "message": "Request timed out",
    "error": "Request Timeout"
  }
}

{
  "status": "error",
  "message": {
    "message": "rate limit exceeded",
    "error": "Too Many Requests"
  }
}

{
  "status": "error",
  "message": {
    "message": "Failed to convert text to speech",
    "error": "Internal Server Error"
  }
}

POST

predict-duration

{voice_id}

Predict text-to-speech duration

curl --request POST \
  --url https://supertoneapi.com/v1/predict-duration/{voice_id} \
  --header 'Content-Type: application/json' \
  --header 'x-sup-api-key: <api-key>' \
  --data '
{
  "text": "<string>",
  "style": "<string>",
  "model": "sona_speech_1",
  "output_format": "wav",
  "voice_settings": {
    "pitch_shift": 0,
    "pitch_variance": 1,
    "speed": 1,
    "duration": 0,
    "similarity": 3,
    "text_guidance": 1,
    "subharmonic_amplitude_control": 1
  }
}
'

import requests

url = "https://supertoneapi.com/v1/predict-duration/{voice_id}"

payload = {
    "text": "<string>",
    "style": "<string>",
    "model": "sona_speech_1",
    "output_format": "wav",
    "voice_settings": {
        "pitch_shift": 0,
        "pitch_variance": 1,
        "speed": 1,
        "duration": 0,
        "similarity": 3,
        "text_guidance": 1,
        "subharmonic_amplitude_control": 1
    }
}
headers = {
    "x-sup-api-key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-sup-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    text: '<string>',
    style: '<string>',
    model: 'sona_speech_1',
    output_format: 'wav',
    voice_settings: {
      pitch_shift: 0,
      pitch_variance: 1,
      speed: 1,
      duration: 0,
      similarity: 3,
      text_guidance: 1,
      subharmonic_amplitude_control: 1
    }
  })
};

fetch('https://supertoneapi.com/v1/predict-duration/{voice_id}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://supertoneapi.com/v1/predict-duration/{voice_id}"

	payload := strings.NewReader("{\n  \"text\": \"<string>\",\n  \"style\": \"<string>\",\n  \"model\": \"sona_speech_1\",\n  \"output_format\": \"wav\",\n  \"voice_settings\": {\n    \"pitch_shift\": 0,\n    \"pitch_variance\": 1,\n    \"speed\": 1,\n    \"duration\": 0,\n    \"similarity\": 3,\n    \"text_guidance\": 1,\n    \"subharmonic_amplitude_control\": 1\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-sup-api-key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://supertoneapi.com/v1/predict-duration/{voice_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'text' => '<string>',
    'style' => '<string>',
    'model' => 'sona_speech_1',
    'output_format' => 'wav',
    'voice_settings' => [
        'pitch_shift' => 0,
        'pitch_variance' => 1,
        'speed' => 1,
        'duration' => 0,
        'similarity' => 3,
        'text_guidance' => 1,
        'subharmonic_amplitude_control' => 1
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-sup-api-key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

HttpResponse<String> response = Unirest.post("https://supertoneapi.com/v1/predict-duration/{voice_id}")
  .header("x-sup-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"text\": \"<string>\",\n  \"style\": \"<string>\",\n  \"model\": \"sona_speech_1\",\n  \"output_format\": \"wav\",\n  \"voice_settings\": {\n    \"pitch_shift\": 0,\n    \"pitch_variance\": 1,\n    \"speed\": 1,\n    \"duration\": 0,\n    \"similarity\": 3,\n    \"text_guidance\": 1,\n    \"subharmonic_amplitude_control\": 1\n  }\n}")
  .asString();

{
  "duration": 123
}

{
  "status": "error",
  "message": "Invalid request data"
}

{
  "status": "error",
  "message": {
    "message": "Invalid API Key",
    "error": "Unauthorized"
  }
}

{
  "status": "error",
  "message": {
    "message": "Not enough credits",
    "error": "Payment Required"
  }
}

{
  "status": "error",
  "message": {
    "message": "Permission denied",
    "error": "Forbidden"
  }
}

{
  "status": "error",
  "message": {
    "message": "Voice not found",
    "error": "Not Found"
  }
}

{
  "status": "error",
  "message": {
    "message": "Request timed out",
    "error": "Request Timeout"
  }
}

{
  "status": "error",
  "message": {
    "message": "rate limit exceeded",
    "error": "Too Many Requests"
  }
}

{
  "status": "error",
  "message": {
    "message": "Failed to convert text to speech",
    "error": "Internal Server Error"
  }
}

이 문서는 영어 원문을 기반으로 자동 번역되었습니다. 표현이 어색하거나 모호한 부분이 있을 수 있으니, 정확한 내용은 영어 원문을 함께 확인해 주세요.

주어진 입력으로 생성될 음성의 예상 길이(초)를 반환합니다. 비용 예측, UI 힌트 표시, 배치 작업 사전 점검에 유용합니다.

이 엔드포인트는 크레딧을 소비하지 않습니다. 동일한 300자 제한이 적용되며, 자동 청크 분할은 수행하지 않습니다.

엔드포인트

POST https://supertoneapi.com/v1/predict-duration/{voice_id}

경로 파라미터

Name	Required	Description
`voice_id`	✅	대상 보이스의 ID입니다.

요청 본문

Create speech와 동일한 구조입니다 — text, language, style, model, voice_settings — 단, 길이에 영향을 주지 않는 output_format, include_phonemes, normalized_text는 제외됩니다.

Name	Required	Description
`text`	✅	분석할 텍스트입니다. 최대 300자.
`language`	✅	언어 코드입니다. 보이스와 모델이 모두 지원해야 합니다.
`style`	—	감정 스타일입니다. 기본값은 보이스의 첫 번째 스타일입니다.
`model`	—	TTS 모델입니다. 기본값은 `sona_speech_1`.
`voice_settings`	—	`speed`와 `duration`을 통해 길이에 영향을 미칩니다. 전체 표는 Create speech를 참고해 주십시오.

요청 예시

POST /v1/predict-duration/20160a4c5ba38967330c84
x-sup-api-key: $SUPERTONE_API_KEY
Content-Type: application/json

{
  "text": "This is a long-form sentence for duration prediction.",
  "language": "en",
  "style": "neutral"
}

응답

{
  "duration": 3.57
}

길이는 초 단위 float 값으로 반환됩니다.

참고사항

예측 시점과 실제 create_speech 호출 시점에 동일한 model과 speed를 사용해 주십시오 — 두 값 모두 결과에 영향을 미칩니다. 서로 다른 속도로 예측하고 생성하면 길이가 일치하지 않습니다.
크레딧은 차감되지 않습니다. UI 힌트나 예산 사전 점검 용도로 안전하게 사용할 수 있습니다.

함께 보기

Docs: Cost and usage

예측과 예산 책정에 predict_duration을 활용하는 방법입니다.

Create speech

추정치를 검증한 뒤 실제로 오디오를 생성합니다.

Authorizations

x-sup-api-key

string

header

required

Path Parameters

voice_id

string

required

Body

application/json

text

string

required

The text to convert to speech. Max length is 300 characters.

Maximum string length: 300

language

enum<string>

required

Language code of the voice

Available options:

en,

ko,

ja,

bg,

cs,

da,

el,

es,

et,

fi,

hu,

it,

nl,

pl,

pt,

ro,

ar,

de,

fr,

hi,

id,

ru,

vi,

hr,

lt,

lv,

sk,

sl,

sv,

tr,

uk

style

string

The style of character to use for the text-to-speech conversion

model

enum<string>

default:sona_speech_1

The model type to use for the text-to-speech conversion

Available options:

sona_speech_1,

sona_speech_2,

sona_speech_2_flash,

supertonic_api_1,

supertonic_api_3

output_format

enum<string>

default:wav

The desired output format of the audio file (wav, mp3). Default is wav.

Available options:

wav,

mp3

voice_settings

object

Show child attributes

Response

Returns predicted duration of the audio in seconds

duration

number

Supertone API

Voices

Custom voices

Text to speech

Usage

엔드포인트

경로 파라미터

요청 본문

요청 예시

응답

참고사항

함께 보기

Docs: Cost and usage

Create speech

Authorizations

Path Parameters

Body

Response

​엔드포인트

​경로 파라미터

​요청 본문

​요청 예시

​응답

​참고사항

​함께 보기

Docs: Cost and usage

Create speech

Authorizations

Path Parameters

Body

Response

엔드포인트

경로 파라미터

요청 본문

요청 예시

응답

참고사항

함께 보기