Tom Yumต้มยำ
v1 + v2The friend who heard it first and cannot wait to tell you.
- Female
- Thai, English, and Mandarin Chinese
- Best friend
- tomyumpaxa-tts-flash-v2
แกรู้ยัง เมื่อคืนมีเรื่องใหญ่มากเลย ฉันเพิ่งรู้มาสด ๆ ร้อน ๆ เดี๋ยวเล่าให้ฟังนะจ๊ะ
Cast it for#
Tom Yum talks fast and leans in. Sentences run into each other, the level jumps on the good part, and the whole read has the energy of a phone call that starts with แกรู้ยัง.
The register is intimacy through speed. It reads a recap as if the listener missed last night's episode and is about to be caught up, which is a different pull from a presenter's brightness.
- Drama and series recaps
- Episode summaries and spoiler clips that need a friend's urgency.
- Entertainment news
- Celebrity and pop-culture segments read at the pace of a friend with news.
- Social clips
- Short vertical video where the first second has to hook.
Reach for instead
In production#
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
curl -X POST https://api.paxalabs.com/v1/tts \ -H "Authorization: Bearer $PAXA_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "text": "แกรู้ยัง เมื่อคืนมีเรื่องใหญ่มากเลย ฉันเพิ่งรู้มาสด ๆ ร้อน ๆ เดี๋ยวเล่าให้ฟังนะจ๊ะ", "voice": "tomyum", "model": "paxa-tts-flash-v2" }' \ --output tomyum.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: "แกรู้ยัง เมื่อคืนมีเรื่องใหญ่มากเลย ฉันเพิ่งรู้มาสด ๆ ร้อน ๆ เดี๋ยวเล่าให้ฟังนะจ๊ะ", voice: "tomyum", model: "paxa-tts-flash-v2", }), }); if (!response.ok) throw new Error(`TTS failed: ${response.status}`); await writeFile("tomyum.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": "แกรู้ยัง เมื่อคืนมีเรื่องใหญ่มากเลย ฉันเพิ่งรู้มาสด ๆ ร้อน ๆ เดี๋ยวเล่าให้ฟังนะจ๊ะ", "voice": "tomyum", "model": "paxa-tts-flash-v2", }, ) response.raise_for_status() with open("tomyum.mp3", "wb") as f: f.write(response.content)
Questions#
Is it too fast for information content?
The speed is the register. Explainers and news bulletins want Foi Thong or Thong Ek, which keep a listener oriented.
How is it different from Nom Yen?
Nom Yen is bright and public, a presenter speaking to a room. Tom Yum is fast and private, a friend speaking to one person, and it runs sentences together where Nom Yen keeps them clean.
Does it read English words?
Yes. Every Paxa TTS Flash v2 voice speaks English, Thai, and Mandarin, even in the same sentence, and social copy is full of English words.
Hear it read your own words. New accounts start with 100 free credits. Open the playground and this voice is already selected.
Start free