Introducing ChindaTTS — Production Thai-English Text-to-Speech, Now Live
Today we are launching ChindaTTS, our production neural Thai + English text-to-speech engine. It speaks natural Thai with correct prosody, reads numbers, dates, money and code-switched text the way a person would, handles long-form narration cleanly, and can clone a voice from a short consented sample — all behind one API, at the iApp TTS v3 address.
Updated 5 October 2026: a third voice, Kaidang, and the voice and style are now chosen in each API request.
Hear all three voices on the ChindaTTS page, and try every voice and style in the API demo.
Why ChindaTTS
General-purpose TTS has always treated Thai as an afterthought — wrong tones, mangled final consonants, robotic delivery, and a complete inability to mix Thai with English. ChindaTTS was built for Thai from the ground up. The result is speech that sounds like a real Thai speaker, even when the sentence is full of numbers, English loanwords, and brand names.
What it does
- Thai + English + code-switch in one request. The text frontend reads numbers, dates, currency, percentages, phone/ID runs, abbreviations, emails, URLs, ALL-CAPS emphasis, and English tech loanwords naturally.
- Correct central-Thai accent. Pure-English passages automatically switch to a native-English mode, per sentence.
- Long-form, spoken in full — no run-on, no cut-off — up to ~100 seconds per request.
- 3 voices (Kaitom, Kaimook, Kaidang) × 8 speaking styles (neutral, friendly, cheerful, calm, serious, sad, excited, empathetic).
- Voice cloning from ~10–20 seconds of consented audio; stateless — used once, never stored.
- One call, one file — text, voice and style in; a WAV or MP3 file at 48 kHz out.
Hear it for yourself
These are real, unedited ChindaTTS samples. Choose a voice, then play any of the eight styles in it. To try your own text, or clone a voice live, use the API demo.
选择音色
Speaking stylesKaitom
- Neutralวันนี้เป็นวันที่อากาศดี เหมาะแก่การออกไปทำกิจกรรมต่างๆ นอกบ้าน0:05
- Friendlyสวัสดีครับ ยินดีที่ได้รู้จักนะครับ มีอะไรให้ช่วยบอกได้เลยนะครับ0:04
- Cheerfulข่าวดีครับ วันนี้เรามีโปรโมชั่นพิเศษ ลดราคาสูงสุดถึงห้าสิบเปอร์เซ็นต์เลยนะครับ0:06
- Calmค่อยๆ หายใจเข้าลึกๆ แล้วผ่อนลมหายใจออกช้าๆ ปล่อยให้ร่างกายผ่อนคลายลง0:06
- Seriousโปรดทราบ ระบบจะปิดปรับปรุงในเวลาเที่ยงคืน กรุณาบันทึกข้อมูลของท่านให้เรียบร้อย0:07
- Sadเราเสียใจอย่างสุดซึ้งต่อการสูญเสียในครั้งนี้ ขอแสดงความเสียใจกับครอบครัวด้วยครับ0:06
- Excitedสุดยอดไปเลย เราเพิ่งคว้ารางวัลชนะเลิศมาได้สำเร็จ ทุกคนดีใจกันมากจริงๆ0:05
- Empatheticเราเข้าใจความรู้สึกของคุณดีนะครับ ไม่ต้องกังวลไป เราจะคอยอยู่ช่วยเหลือเสมอ0:06
What it reads
ChindaTTS Prime
ChindaTTS Prime, on in the API and a setting on your own servers, adds a speech-recognition gate that re-rolls a garbled or cut take — it selects a better take, it does not alter the audio. Same sound; the gain is stability on hard inputs, especially expressive styles.
| Metric — CER (lower is better) | ChindaTTS | ChindaTTS Prime |
|---|---|---|
| Everyday text | 3.2% | 3.2% |
| Numbers / dates / currency | 1.8% | 1.4% |
| Code-switch | 7.9% | 7.6% |
| Expressive styles | 8.3% | 3.9% |
| Bad-take rate (styles) | 15.0% | 6.7% |
| Worst-case p90 (styles) | 31.8% | 11.4% |
Everyday text already sits at the recognizer noise floor; Prime's value shows up on expressive styles, cutting the bad-take rate by more than half.
Speed (per GPU, ~6–7× real-time)
| Request | Audio | Processing |
|---|---|---|
| ~100 chars | ~9 s | ~1.5 s |
| ~300 chars | ~25 s | ~4 s |
| ~1000 chars | ~90 s | ~14 s |
Throughput scales by adding GPUs.
Where it fits
Voice assistants and IVR, in-app and announcement narration, accessibility, e-learning, notifications, and any product that needs a natural Thai voice that also handles English without breaking stride.
Spread the word
Try ChindaTTS
- Listen to the samples: ChindaTTS
- Product page & specs: iapp.co.th/products/chindaTTS
- Talk to us about a pilot: sale@iapp.co.th
ChindaTTS is production-ready for pilots today: the three voices, the eight styles, cloning and Prime are live in the API and tested. We can't wait to hear what you build with it.