Thong Ekทองเอก
Bulletin pace, with the consonant attack a news read depends on.
Male · Thai · News anchor · 0:03thongek
สวัสดีครับ ข่าวภาคค่ำวันนี้ เริ่มต้นที่สภาพอากาศทั่วประเทศครับ
The clip opens an evening bulletin. Listen to the attack on ข่าวภาคค่ำ and the clean break before the weather line.
Thong Ek reads the way a Thai bulletin reads. Consonants land hard, the pace stays forward, and the level holds steady through a paragraph of facts.
The same qualities make it the roster's announcement voice. Anything a listener hears while half paying attention benefits from a read this legible.
Cast it for#
- News and bulletins
- Headlines, wire copy, and daily briefs in Thai.
- Corporate updates
- Quarterly notes, policy changes, and internal announcements.
- Public announcements
- Station, queue, and safety copy heard once and never repeated.
Reach for instead
- Khanom Krok Feature narration wants a slower read that lets a subject breathe.
- Massaman Dramatic copy wants weight ahead of clarity.
In production#
- Announcements
Public and platform announcements.
- Publishers
Daily briefs and headline audio.
- Call centers
Queue messages and menu prompts.
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": "สวัสดีครับ ข่าวภาคค่ำวันนี้ เริ่มต้นที่สภาพอากาศทั่วประเทศครับ",
"voice": "thongek",
"model": "paxa-tts-flash-v1"
}' \
--output thongek.mp3import { 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: "สวัสดีครับ ข่าวภาคค่ำวันนี้ เริ่มต้นที่สภาพอากาศทั่วประเทศครับ",
voice: "thongek",
model: "paxa-tts-flash-v1",
}),
});
if (!response.ok) throw new Error(`TTS failed: ${response.status}`);
await writeFile("thongek.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": "สวัสดีครับ ข่าวภาคค่ำวันนี้ เริ่มต้นที่สภาพอากาศทั่วประเทศครับ", "voice": "thongek", "model": "paxa-tts-flash-v1"},
)
response.raise_for_status()
with open("thongek.mp3", "wb") as f:
f.write(response.content)- Model
- Paxa TTS Flash
- Per request
- 5,000 characters
- Rate
- 15 credits per 1,000 characters
- Free credits
- 100 credits, about 9 minutes
Questions#
- Does it suit automated announcements?
- Yes. Station and queue copy wants this kind of legibility, and the register is written for a listener who is half paying attention.
- Can it read material that is not news?
- It reads any Thai text. The bulletin cadence stays, which suits corporate updates and safety notices and works against bedtime stories.
- Which English voice matches it?
- Toast reads English at comparable everyday clarity. For English brand and campaign lines with more polish, Latte is the closer match.
Hear it read your own words.
New accounts start with 100 free credits. Open the playground and this voice is already selected.