
Woonวุ้น
The quietest voice in the roster, kept just above a whisper.
Female · Thai · Whisper · 0:04woon
หลับตาเบา ๆ นะคะ คืนนี้ขอให้ฝันดี ราตรีสวัสดิ์ค่ะ
The clip is a goodnight. Listen for the breath before ราตรีสวัสดิ์ค่ะ, which the register keeps rather than edits away.
Woon reads at the edge of voice. Breath is audible, consonants soften, and the whole delivery assumes a listener already lying down in the dark.
It is a specialist for endings. Material that has to be understood on the first pass belongs to a fuller register, and everything Woon is for is heard by someone on their way out of the day.
Cast it for#
- Bedtime stories
- Short reads for children that are meant to end in sleep.
- Wind-down tracks
- The last few minutes of a sleep app or a calm playlist.
- Whisper and close-mic audio
- Material produced for headphones where quiet is the effect.
Reach for instead
In production#
- Creators
Sleep apps and whisper-audio channels.
- Audiobooks
Short bedtime reading.
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": "หลับตาเบา ๆ นะคะ คืนนี้ขอให้ฝันดี ราตรีสวัสดิ์ค่ะ",
"voice": "woon",
"model": "paxa-tts-flash-v1"
}' \
--output woon.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: "หลับตาเบา ๆ นะคะ คืนนี้ขอให้ฝันดี ราตรีสวัสดิ์ค่ะ",
voice: "woon",
model: "paxa-tts-flash-v1",
}),
});
if (!response.ok) throw new Error(`TTS failed: ${response.status}`);
await writeFile("woon.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": "หลับตาเบา ๆ นะคะ คืนนี้ขอให้ฝันดี ราตรีสวัสดิ์ค่ะ", "voice": "woon", "model": "paxa-tts-flash-v1"},
)
response.raise_for_status()
with open("woon.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#
- Is it audible on a speaker?
- The register is written for headphones and a quiet room. Played across a room it loses consonants. Foi Thong or Lod Chong hold up where this one does not.
- How is it different from Lod Chong?
- Lod Chong keeps full voice at a low level. A guided instruction stays clear from start to finish. Woon drops below that, closer to a whisper, for the minutes when clarity matters less.
- Can it read a whole book?
- Short bedtime pieces suit it. Across a full book the near-whisper stops carrying, and a listener who is still awake will lose the thread.
Hear it read your own words.
New accounts start with 100 free credits. Open the playground and this voice is already selected.