Pad Thaiผัดไทย

Cast it for#

Event hosting

Conference links, stage announcements, and run-of-show copy in both languages.

Lifestyle and entertainment

Shows and channels where English terms arrive in every second line.

Bilingual product copy

Feature names, plan names, and interface terms that stay in English inside Thai sentences.

Reach for instead

• Nom Yen Thai-first product speech, where English appears occasionally.
• Donut Copy written entirely in English wants an English-first voice.

In production#

• Creators

  Hosted shows and bilingual channels.

• Announcements

  Event and stage announcements.

• E-learning

  Courses that teach in Thai with English terms.

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": "สวัสดีค่ะ welcome back to the show ค่ะ วันนี้เรามี special guest มาด้วยค่ะ",
    "voice": "padthai",
    "model": "paxa-tts-flash-v1"
  }' \
  --output padthai.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: "สวัสดีค่ะ welcome back to the show ค่ะ วันนี้เรามี special guest มาด้วยค่ะ",
    voice: "padthai",
    model: "paxa-tts-flash-v1",
  }),
});

if (!response.ok) throw new Error(`TTS failed: ${response.status}`);
await writeFile("padthai.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": "สวัสดีค่ะ welcome back to the show ค่ะ วันนี้เรามี special guest มาด้วยค่ะ", "voice": "padthai", "model": "paxa-tts-flash-v1"},
)
response.raise_for_status()

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

API voice reference

Related voices#

Questions#

Do the other voices handle English too?

Every Paxa TTS Flash voice reads Thai and English in one sentence. Pad Thai is cast for scripts where the switch is constant, and the register was written with that rhythm in mind.

How does it read English on its own?

It reads English with a Thai speaker's accent, which is the right choice for a Thai audience. For copy aimed at English speakers, Donut and Cookie are the English-first voices.

Does it handle brand names in Latin script?

Yes. Product names, plan names, and interface terms stay in English inside a Thai line, and the level holds across the switch.