Skip to main content
Core.Today
|
NCP ClovaFastHigh

Clova Voice TTS Premium

NAVER Clova Voice Premium TTS with 108 voices across 6 languages. High-quality Korean voice synthesis with emotion control, Pro voices, and bilingual support.

12.4 credits
per 100 characters (0.124 credits/char, rounded up per 100 chars)
108 voice options across 6 languages
High-quality Korean voice synthesis
Emotion control (neutral, sad, happy, angry)
9 Pro-quality premium voices
Bilingual Korean+English voices
Volume, speed, pitch fine-tuning

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txt

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "ncp-clova/tts-premium",
  "input": {
    "text": "์•ˆ๋…•ํ•˜์„ธ์š”, ์ฝ”์–ด๋‹ทํˆฌ๋ฐ์ด์ž…๋‹ˆ๋‹ค. ์ตœ๊ณ ์˜ AI ์„œ๋น„์Šค๋ฅผ ๊ฒฝํ—˜ํ•ด ๋ณด์„ธ์š”!",
    "speaker": "vara",
    "emotion": 2,
    "emotion-strength": 2,
    "speed": 0,
    "format": "mp3"
  }
}'

Voice Gallery

Preview 108 preset voices

์•„๋ผ ProF
๋Œ€์„ฑ ProM
๋‹ค์ธ ProF
๋™ํ˜„ ProM
๊ณ ์€ ProF
ํ˜œ๋ฆฌ ProF
์ด์•ˆ ProM
๋ฏธ๊ฒฝ ProF
์œ ๋‚˜ ProF
์•„๋ผ&์•ˆ๋‚˜ (์ด์ค‘์–ธ์–ด)F
์‹ ์šฐ&๋งคํŠธ (์ด์ค‘์–ธ์–ด)M
์•„๋ผF
์•„๋ผ (์ƒ๋‹ด์›)F
์•„๋ผ (ํ™”๋‚จ)F
๋ณด๋ผF
๋‹ค์ธF
์€์„œF
์€์˜F
๊ฐ€๋žŒF
๊ณ ์€F
ํฌ๋ผF
์ดํ˜„F
๋“œ๋ฆผF
์ง€์›F
์ง€์œคF
๊ฒฝ๋ฆฌF
๋ฏธ์ง„F
๋ฏผ์ •F
๋ฏผ์„œF
๋ฏผ์˜F
๋ด„๋‹ฌF
๋งˆ๋…€ ์‚ฌ๋น„๋‚˜F
์ƒค์ƒคF
์ˆ˜์ง„F
์„ ํฌF
์„ ๊ฒฝF
๊ธฐ์„œF
์˜ˆ์ง€F
์˜ˆ์ง„F
์ •์˜ํ™”F
์˜๋ฏธF
์œ ์ง„F
์œ ๋‚˜F
๋ฏธ์ง„ (Classic)F
๋Š˜๋ด„F
ํ˜œ๋ฆฌF
๋ฏธ๊ฒฝF
์†Œํ˜„F
์•ผ์˜น์ดF
๋ฏผ์ƒM
์ง„ํ˜ธM
๋Œ€์„ฑM
๋™ํ˜„M
์€์šฐM
๊ฒฝ์ค€M
์ด์•ˆM
์žฌ์šฑM
์ง€ํ›ˆM
์ง€ํ™˜M
์ข…ํ˜M
์ข…ํ˜„M
์ฃผ์•ˆM
์ค€์˜M
๊ธฐํƒœM
๊ฒฝํƒœM
๊ทœ์›M
์•…๋งˆ ๋งˆ๋ชฌM
์ตœ๋ฌด๋น„M
๋ž˜์›M
๋ฐ•๋ฆฌ๋ทฐM
์ƒ๋„M
์„ฑํ›ˆM
์Šนํ‘œM
์‹ ์šฐM
์‹œ์œคM
ํƒœ์ง„M
์›ํƒM
์šฐ์‹M
์˜์ผM
์ง„ํ˜ธ (Classic)M
๊ธฐํšจM
ํ•˜์ค€M
๋ฉ๋ฉ์ดM
์‹ ์ง€M
์•„์œ ๋ฌดM
๋‹ค์ดํ‚คM
์—๋ฆฌ์ฝ”F
ํ•˜์ง€๋ฉ”M
๋ฏธ์˜คF
๋‚˜์˜ค๋ฏธF
๋‚˜์˜ค๋ฏธ (๋‰ด์Šค)F
๋‚˜์˜ค๋ฏธ (๊ธฐ์จ)F
๋ฆฌ์ฝ”F
์‚ฌ์œ ๋ฆฌF
ํ† ๋ชจ์ฝ”F
๋‚˜์˜ค๋ฏธ (N)F
์‚ฌ์œ ๋ฆฌ (N)F
ํ† ๋ชจ์ฝ” (N)F
ClaraF
AnnaF
JoeyF
MattM
๋Ÿ‰๋Ÿ‰M
๋ฉ”์ด๋ฉ”์ดF
CarmenF
JosรฉM
์ฐจํ™”F
๊ด€๋ฆฐM

Sample: "Hello? Welcome to Core.Today" ยท Click voice_id to copy

Parameters

ParameterTypeRequiredDefaultDescription
textstringYes-Text to synthesize (UTF-8). Korean/Chinese/Japanese/Taiwanese max 2,000 chars, English/Spanish max 3,000 chars.
speakerstringYesnaraVoice ID. 108 voices: 81 Korean, 15 Japanese, 4 English, 2 Korean+English, 2 Chinese, 2 Spanish, 2 Taiwanese.
volumeintegerNo0Volume (-5 to 5, default 0)
speedintegerNo0Speed (-5 to 10, default 0)
pitchintegerNo0Pitch (-5 to 5, default 0)
emotionintegerNo0Emotion (0: neutral, 1: sad, 2: happy, 3: angry). Supported by select voices only.
0123
emotion-strengthintegerNo1Emotion strength (0: weak, 1: normal, 2: strong)
012
formatstringNomp3Audio output format
mp3wav

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Korean TTS with Emotion

Generate Korean speech with happy emotion using the default 'nara' voice

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "ncp-clova/tts-premium",
  "input": {
    "text": "์•ˆ๋…•ํ•˜์„ธ์š”, ์ฝ”์–ด๋‹ทํˆฌ๋ฐ์ด์ž…๋‹ˆ๋‹ค. ์ตœ๊ณ ์˜ AI ์„œ๋น„์Šค๋ฅผ ๊ฒฝํ—˜ํ•ด ๋ณด์„ธ์š”!",
    "speaker": "vara",
    "emotion": 2,
    "emotion-strength": 2,
    "speed": 0,
    "format": "mp3"
  }
}'

Tips & Best Practices

1Use Pro voices (vara, vgoeun, etc.) for the highest quality Korean speech
2Emotion control is only supported by select Korean voices - test with nara first
3For Korean+English bilingual content, use dara-danna (female) or dsinu-matt (male)
4Keep text under 2,000 characters for Korean/Chinese/Japanese and 3,000 for English/Spanish

Use Cases

Korean content narration
Multilingual customer service
E-learning and educational content
Interactive voice response (IVR)
Audiobook production
Character voice acting