Text to speech · 한국어
Pāṇini TTS reads Korean Hangul in the polite speech levels Korean customer service relies on, with Taeyang, a native Korean voice.
Sonex 카드입니다. 이번 달 결제 금액 삼십이만 원이 십일월 오일에 출금될 예정입니다. 결제 전 본인 확인을 위해 OTP 번호를 SMS로 보내 드릴게요.
Voices
Free to play in your browser without an account, up to 220 characters at a time. To save the audio as a file, sign up free for 10,000 characters and one voice clone, no card required: the dashboard saves WAV and the API returns MP3.
Making a video? See AI voice-over for YouTube and Reels. The audio is yours to use on monetised channels.
Last verified 24 October 2026
Taeyang, a native Korean platform voice, reads the playground above. Any Sonex Labs voice can also read Korean, keeping its own accent, and a voice cloned from a 10-second recording of a Korean speaker carries that speaker's accent.
Sign up free, then send Korean text to the API with "output_format": "mp3" and save the file, or generate clips in the dashboard and download them. Scripts longer than the playground's 220 characters work the same way.
About Korean
Hangul is an alphabet whose letters are stacked into syllable blocks: ㅎ, ㅏ and ㄴ make 한. Spelling is regular, but pronunciation changes at the boundaries between blocks, so 감사합니다 (thank you) is said gam-sa-ham-ni-da, and 국물 becomes gung-mul. A voice that reads each block on its own sounds robotic. Korean also has two number systems: native numbers for hours and counting (세 시, three o'clock) and Sino-Korean numbers for minutes, money and dates (삼십 분, thirty minutes).
Speech levels carry politeness. Calls to customers use the formal -습니다 ending and honorific forms like 고객님 (valued customer) and 말씀해 주세요 (please tell me), with the softer -요 ending for warmer moments. Getting this wrong is noticed instantly. Korean customer text borrows English heavily, written in Hangul: 앱 (app), 쿠폰 (coupon), 배송 조회 next to 택배 (parcel delivery). Shopping, finance and healthcare booking in Korea run largely through apps, and their notification calls must sound like a careful human agent. The samples here are read by Taeyang, a native Korean platform voice.
Use cases
Clinics and hospitals confirm 진료 예약 (appointments) and send reminders in honorific Korean.
Couriers and delivery apps announce arrival times and handle redelivery requests by voice.
Banks and card companies read payment due dates and fraud alerts in the formal register.
Commercial use
The full wording is in our terms of service.
YouTube
Yes, AI voices are allowed. What YouTube limits is mass-produced, repetitive content: videos made from a template with little original work. Its July 2025 update renamed that rule from “repetitious” to “inauthentic” content (YouTube’s monetisation policies).
Write your own script, add your own research or editing, and keep one consistent voice for the channel. Where a realistic AI voice could mislead viewers, use YouTube’s altered or synthetic content label. The monetisation decision is always YouTube’s.
Voice cloning
Clone your voice from a 10-second recording. Your clone speaks Korean, and every other language Pāṇini supports, in your own voice. The language comes from the text you type, so a clone recorded in English or Hindi can read a Korean script.
Your accent comes with it: a clone sounds like you speaking Korean, not like a different native speaker. Every free account includes one voice clone. Clone only your own voice, or a voice whose owner has agreed.
API
One request returns Korean audio as MP3. The language is detected from the text, so no language setting is needed. Pāṇini TTS starts streaming audio in under 200 ms (time to first byte).
1curl https://api.sonexlabs.com/v1/speech \2 --header 'Authorization: Bearer YOUR_API_KEY' \3 --header 'Content-Type: application/json' \4 --data '{"text": "Sonex 카드입니다. 이번 달 결제 금액 삼십이만 원이 십일월 오일에 출금될 예정입니다. 결제 전 본인 확인을 위해 OTP 번호를 SMS로 보내 드릴게요.", "output_format": "mp3"}' \5 --output korean.mp3FAQ
Yes. The playground on this page reads up to 220 characters of Korean at a time with no account. Sign up free for 10,000 characters and one voice clone, no card; after that it costs $0.03125 per 1,000 characters.
Yes, after free sign-up. The playground on this page plays audio in your browser only, up to 220 characters at a time, so you can check the voice first. Sign up free (10,000 characters and one voice clone, no card): the dashboard saves each clip as a WAV file with Download audio, and the API returns MP3 when you set "output_format": "mp3".
Yes. Taeyang is a native Korean voice. Any Sonex Labs voice can also speak Korean, and you can clone your own from a 10-second sample.
Writing numbers in Hangul (세 시, 삼십 분) gives you exact control; digits are read in the usual form for their context.
It reads the speech level you write, so -습니다 and honorific forms sound as formal as intended.
$0.03125 per 1,000 characters, the same as every language.
Yes. Audio you generate, on the free tier or with paid credits, can be used on monetised YouTube channels, Shorts, Reels and in ads, with no attribution. YouTube limits mass-produced, repetitive videos, not AI voices, so write your own script and keep your edits original. The monetisation decision is YouTube's.
The audio you generate is yours to use, including commercially, with no attribution and no royalties to Sonex Labs. You are responsible for the script itself: if you read someone else's text, you need their permission.
Yes. A Sonex voice clone is not tied to the language it was recorded in. Type a Korean script and your clone reads it in your own voice, with Korean pronunciation. Your natural accent carries over, so it sounds like you speaking Korean.
More languages
See text to speech in every language, the full list of 250+ languages, pricing, the Pāṇini TTS API, or transcribe Korean audio with Valmiki speech to text.
10,000 free text-to-speech characters and one free voice clone that speaks every language, no card required. Every language is billed at the same rate.