
Latteลาเต้
The finished read, for copy that has been through the agency.
Male · English · Brand films · 0:03latte
Every great brand has a story. Tonight, we're going to tell yours.
The clip is a brand line in two halves. Listen to the pause between them, which is where the composure shows.
Latte reads English with finish. Consonants are clean, the pace is measured, and the whole delivery has the composure a brand film is scored around.
The polish sets its range. It suits copy written to be admired, and it sits oddly on a walkthrough, where a viewer needs a person on screen and gets a performance.
Cast it for#
- Brand films
- Company and product films where the read carries the production value.
- Launch and campaign video
- English copy that has to sound considered on the first hearing.
- Premium narration
- Hospitality, automotive, and lifestyle work read at an unhurried pace.
Reach for instead
In production#
- Announcements
Brand and launch films in English.
- Creators
Premium channel and campaign video.
- Publishers
Feature openers and sponsored narration.
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": "Every great brand has a story. Tonight, we're going to tell yours.",
"voice": "latte",
"model": "paxa-tts-flash-v1"
}' \
--output latte.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: "Every great brand has a story. Tonight, we're going to tell yours.",
voice: "latte",
model: "paxa-tts-flash-v1",
}),
});
if (!response.ok) throw new Error(`TTS failed: ${response.status}`);
await writeFile("latte.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": "Every great brand has a story. Tonight, we're going to tell yours.", "voice": "latte", "model": "paxa-tts-flash-v1"},
)
response.raise_for_status()
with open("latte.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 too polished for casual content?
- The finish is the register. On a walkthrough or a vlog it reads as distance, and Toast covers that ground in the same band.
- Can it read Thai?
- It reads Thai with a foreign accent, since the voice is designed around English. Thai brand films want Massaman or Panang, depending on whether the copy needs weight or articulation.
- How is it different from Massaman?
- Massaman is the Thai low end, built for trailers in Thai. Latte is English-first and sits higher, with polish where Massaman brings weight.
Hear it read your own words.
New accounts start with 100 free credits. Open the playground and this voice is already selected.