Khanom Krokขนมครก

Cast it for#

Documentary and heritage

Thai narration where the subject supplies the energy and the voice stays out of its way.

Chapter-length reads

Non-fiction audiobooks and serialised features that run for twenty minutes at a time.

Institutional narration

Museum guides, corporate history, and anything a listener expects to sound settled.

Reach for instead

• Thong Ek A bulletin wants the clip and forward pressure of a news read.
• Massaman Trailers and title sequences want the low theatrical weight this register keeps in reserve.

In production#

• Publishers

  Feature narration and archive pieces in Thai.

• Audiobooks

  Non-fiction chapters that a listener stays with.

• E-learning

  Course narration for adult learners.

Call it from the API#

The voice field takes the id above. Every other value in this request is a Paxa TTS Flash default.

curl -X POST https://api.paxalabs.com/v1/tts \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "สมัยผมยังหนุ่ม แถวนี้ยังเป็นทุ่งนา เดินไปตลาดทีหนึ่งก็ค่อนวันแล้วครับ",
    "voice": "khanomkrok",
    "model": "paxa-tts-flash-v1"
  }' \
  --output khanomkrok.mp3

import { writeFile } from "node:fs/promises";

const response = await fetch("https://api.paxalabs.com/v1/tts", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.PAXA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    text: "สมัยผมยังหนุ่ม แถวนี้ยังเป็นทุ่งนา เดินไปตลาดทีหนึ่งก็ค่อนวันแล้วครับ",
    voice: "khanomkrok",
    model: "paxa-tts-flash-v1",
  }),
});

if (!response.ok) throw new Error(`TTS failed: ${response.status}`);
await writeFile("khanomkrok.mp3", Buffer.from(await response.arrayBuffer()));

import os
import requests

response = requests.post(
    "https://api.paxalabs.com/v1/tts",
    headers={"Authorization": f"Bearer {os.environ['PAXA_API_KEY']}"},
    json={"text": "สมัยผมยังหนุ่ม แถวนี้ยังเป็นทุ่งนา เดินไปตลาดทีหนึ่งก็ค่อนวันแล้วครับ", "voice": "khanomkrok", "model": "paxa-tts-flash-v1"},
)
response.raise_for_status()

with open("khanomkrok.mp3", "wb") as f:
    f.write(response.content)

API voice reference

Related voices#

Questions#

How old does Khanom Krok sound?

The register reads as an older man, and the published clip leans into it with a line about rice fields that used to be here. The age is a property of the voice, and it holds across whatever text you send.

How is it different from Thong Ek?

Thong Ek reads at bulletin pace with a hard consonant attack. Khanom Krok runs slower and lands softer, which is what lets it hold a twenty-minute chapter where a news read would tire a listener.

Does it handle English words inside Thai text?

Yes. Every Paxa TTS Flash voice reads Thai and English in one sentence, and a Latin-script brand name inside a Thai line comes back in the same register.