Nom Yenนมเย็น
v1 + v2The roster's female lead, bright enough to open a clip and steady enough to finish one.
- Female
- Thai, English, and Mandarin Chinese
- Lead voice
- nomyenpaxa-tts-flash-v2
ยินดีต้อนรับสู่ Paxa Labs ค่ะ เสียงภาษาไทยที่สลับเป็น English ได้กลางประโยค อย่างเป็นธรรมชาติ
Cast it for#
Nom Yen carries energy without pushing into announcer register. It is the voice most product work reaches for first, covering promos, social clips, in-app prompts, and the short lines an interface speaks all day.
The read stays legible at speed, which matters for copy that has thirty seconds to land. Longer material is where it eventually wears, and the roster has narrators built for that.
- Promos and social
- Short spots and vertical video, where the first two seconds decide whether anyone stays.
- Product speech
- In-app prompts, confirmations, and the small lines an interface repeats every session.
- Mixed Thai and English copy
- Marketing lines carrying brand names, feature names, and loan words in Latin script.
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": "ยินดีต้อนรับสู่ Paxa Labs ค่ะ เสียงภาษาไทยที่สลับเป็น English ได้กลางประโยค อย่างเป็นธรรมชาติ", "voice": "nomyen", "model": "paxa-tts-flash-v2" }' \ --output nomyen.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: "ยินดีต้อนรับสู่ Paxa Labs ค่ะ เสียงภาษาไทยที่สลับเป็น English ได้กลางประโยค อย่างเป็นธรรมชาติ", voice: "nomyen", model: "paxa-tts-flash-v2", }), }); if (!response.ok) throw new Error(`TTS failed: ${response.status}`); await writeFile("nomyen.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": "ยินดีต้อนรับสู่ Paxa Labs ค่ะ เสียงภาษาไทยที่สลับเป็น English ได้กลางประโยค อย่างเป็นธรรมชาติ", "voice": "nomyen", "model": "paxa-tts-flash-v2", }, ) response.raise_for_status() with open("nomyen.mp3", "wb") as f: f.write(response.content)
Questions#
Can it switch between Thai and English in one sentence?
Yes. Every Paxa TTS Flash v2 voice speaks English, Thai, and Mandarin, even in the same sentence. Nom Yen's own published line runs from Thai into English and back, which is the case most Thai product copy presents.
Can the read be slowed down?
Yes. The speed field takes a multiplier from 0.5 to 1.5 on the voice's own design speed, and it changes no charge. The character count is what bills.
How is it different from Foi Thong?
Foi Thong is built to hold attention across a long read at an even level. Nom Yen opens higher and moves quicker, which suits copy measured in seconds.
Hear it read your own words. New accounts start with 100 free credits. Open the playground and this voice is already selected.
Start free