Sangkayaสังขยา

v1 + v2

Close-mic and unhurried, a male voice for quiet listening.

Male
Thai, English, and Mandarin Chinese
Close-mic
sangkayapaxa-tts-flash-v2

ค่อย ๆ วางทุกอย่างลงก่อนนะครับ แล้วพักหูฟังเสียงเบา ๆ แบบนี้สักครู่ครับ

Cast it for#

Sangkaya reads softly and close, with the breath and mouth detail close-mic listening is built on. The register stays male and adult while sitting well below conversational volume.

It covers the ground between calm narration and ASMR. The delivery keeps enough shape to carry a paragraph of meaning, which separates it from the quietest reads.

ASMR: Close-mic material where texture and breath are the content.
Calm narration: Reflective essays and slow features read for headphone listening.
Long-form quiet audio: Study and focus tracks that run for an hour without asking for attention.

Reach for instead

Oliang
Conversational volume with the same low centre, for radio and podcasts.
Lod Chong
Guided sessions in a female register built around instruction.

In production#

Creators

ASMR and focus-audio channels.

Audiobooks

Reflective non-fiction read quietly.

Call it from the API#

The voice field takes the id above. Every other value in this request is a Paxa TTS Flash v2 default.

Model: Paxa TTS Flash v2
Per request: 5,000 characters
Rate: 10 credits per 1,000 characters
Free credits: 100 credits, about 16 minutes

API voice reference

curl -X POST https://api.paxalabs.com/v1/tts \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "ค่อย ๆ วางทุกอย่างลงก่อนนะครับ แล้วพักหูฟังเสียงเบา ๆ แบบนี้สักครู่ครับ",
    "voice": "sangkaya",
    "model": "paxa-tts-flash-v2"
  }' \
  --output sangkaya.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: "ค่อย ๆ วางทุกอย่างลงก่อนนะครับ แล้วพักหูฟังเสียงเบา ๆ แบบนี้สักครู่ครับ",
    voice: "sangkaya",
    model: "paxa-tts-flash-v2",
  }),
});
if (!response.ok) throw new Error(`TTS failed: ${response.status}`);
await writeFile("sangkaya.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": "ค่อย ๆ วางทุกอย่างลงก่อนนะครับ แล้วพักหูฟังเสียงเบา ๆ แบบนี้สักครู่ครับ",
        "voice": "sangkaya",
        "model": "paxa-tts-flash-v2",
    },
)
response.raise_for_status()
with open("sangkaya.mp3", "wb") as f:
    f.write(response.content)

Questions#

How is it different from Oliang?

Oliang talks at conversational volume with a slack, radio pace. Sangkaya drops below that to close-mic level, where breath becomes part of what a listener hears.

Is it a whisper?

It keeps full voice at a low level. Woon reads quieter still, and this register stays intelligible across a longer piece than a whisper would.

Does it work for regular narration?

For reflective and slow material it holds. Anything that has to be understood over background noise wants Khanom Krok or Thong Ek.

Hear it read your own words. New accounts start with 100 free credits. Open the playground and this voice is already selected.

Start free