State‑of‑the‑art speech and language AI, native in Thai and English
Paxa TTS Flash, our flagship text-to-speech model, speaks both languages naturally, even in the same sentence.
100 free credits to start, no card required.
Hear Thai, natively
Nom Yen
Female · Thai and English
Bright, energetic voice and the roster's female lead: promos, social clips, and everyday product speech.
ยินดีต้อนรับสู่ Paxa Labs ค่ะ เสียงภาษาไทยที่สลับเป็น English ได้กลางประโยค อย่างเป็นธรรมชาติ
Nom Yen
0:06ยินดีต้อนรับสู่ Paxa Labs ค่ะ เสียงภาษาไทยที่สลับเป็น English ได้กลางประโยค อย่างเป็นธรรมชาติ
The Speech page takes longer text, word timestamps, and audio you can download.
Products
Models & voices
Paxa TTS Flash
v1Our flagship text-to-speech model for natural Thai and English speech.
- Languages
- TH · EN
- Voices
- 26
- Khanom Krok
- Nom Yen
- Tako
- Foi Thong
- Massaman
- Thong Ek
- Panang
- Oliang
- Sanae Chan
- Tub Tim Krob
- Moo Ping
- Bua Loi
- Luk Chup
- Lod Chong
- Woon
- Sangkaya
- Pad Thai
- Yoyo
- Som Tam
- Larb
- Khao Soi
- Roti
- Donut
- Cookie
- Toast
- Latte
From news anchor to ASMR, in Thai, Isan, Northern, and Southern accents, plus English-first voices.
Pro
Coming soonThe next generation of Paxa speech synthesis.
Translation
Paxa Translate Lite writes the Thai a native reader expects, from any of 14 source languages.
Welcome to our store. Free shipping on orders over 500 baht.
ยินดีต้อนรับสู่ร้านของเรา ส่งฟรีเมื่อสั่งซื้อครบ 500 บาท
Formality, glossaries, and document context are request options on the same API. See the English to Thai translation API
Build with one API
curl -X POST https://api.paxalabs.com/v1/tts \
-H "Authorization: Bearer $PAXA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "สวัสดีครับ ยินดีต้อนรับสู่ Paxa Labs",
"voice": "khanomkrok",
"model": "paxa-tts-flash-v1"
}' \
--output speech.mp3# --max-time covers a large request; curl defaults to no limit,
# but most clients and SDKs time out well before a big translation ends.
curl -X POST https://api.paxalabs.com/v1/translate \
--max-time 300 \
-H "Authorization: Bearer $PAXA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Welcome to our store. Free shipping on orders over 500 baht.",
"model": "paxa-translation-lite-v1"
}'Streaming, two ways
Chunked audio over plain HTTP, or a live websocket that speaks while your LLM is still writing.
OpenAI-compatible
The speech endpoint answers the OpenAI SDK at /v1/audio/speech. Swap the base URL and nothing else.
Timed speech
Ask for timestamps and speech returns word, sentence, or utterance spans for captions and read-along interfaces.
Usage-based billing
Speech at 15 and translation at 25 credits per 1,000 characters, OCR at 6.5 credits per page, counted per request. Failed requests are refunded automatically.
Timed speech
ยินดีต้อนรับ
Nom Yen reading the line from the demo above, with the word spans the timestamps option returns.
Pricing
- Speech credits per 1,000 characters
- 15
- Translation credits per 1,000 characters translated
- 25
- OCR credits per page read
- 6.5
- Starter plan, per month
- $6
One credit balance spends across every API, at the same rates on every plan. Plans, refills, and the market comparison live on the pricing page.
Enterprise
Realtime speech, on capacity reserved for your workload.
- Milliseconds to first audio
- 50
- Faster than real time
- 95×
For voice agents, live dubbing, and anything a person is waiting on. Volume, rate limits, and concurrency are quoted to the workload you run. Both figures are the best results from our own load test on dedicated hardware, and the self-serve plans run on shared capacity.
Built in Bangkok
A research lab in Bangkok inventing speech and language models for Thai speakers, without compromising English.
- Languages, Thai and English
- 2
- Models in the lab
- 4
- Voices in the Flash catalog
- 26