Donutโดนัท
v1 onlyThe opener of the English band, bright from the first word.
- Female
- English
- Promos
- donutpaxa-tts-flash-v1
Hey everyone! Welcome back to the channel. Today we have something really fun to share.
Cast it for#
Donut reads English with the energy of a channel host who knows the first line decides everything. The register is warm, quick, and unmistakably built for video.
It is one of 6 English-first voices. Those voices are designed around English and carry a foreign accent when handed Thai, which is why the roster keeps the two groups apart.
- Promos and demos
- Product videos and launch clips for an English-speaking audience.
- Channel openers
- Intros and endcards where energy has to arrive before information does.
- Event and campaign spots
- Short English copy that carries excitement as part of the message.
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 default.
- Model
- Paxa TTS Flash
- Per request
- 5,000 characters
- Rate
- 10 credits per 1,000 characters
- Free credits
- 100 credits, about 11 minutes
curl -X POST https://api.paxalabs.com/v1/tts \ -H "Authorization: Bearer $PAXA_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "text": "Hey everyone! Welcome back to the channel. Today we have something really fun to share.", "voice": "donut", "model": "paxa-tts-flash-v1" }' \ --output donut.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: "Hey everyone! Welcome back to the channel. Today we have something really fun to share.", voice: "donut", model: "paxa-tts-flash-v1", }), }); if (!response.ok) throw new Error(`TTS failed: ${response.status}`); await writeFile("donut.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": "Hey everyone! Welcome back to the channel. Today we have something really fun to share.", "voice": "donut", "model": "paxa-tts-flash-v1", }, ) response.raise_for_status() with open("donut.mp3", "wb") as f: f.write(response.content)
Questions#
Can it read Thai?
It reads Thai with a foreign accent, since the voice is designed around English. For Thai copy, the roster's Thai voices are the right choice, and they read English terms inside Thai lines.
How is it different from Cookie?
Cookie reads level and patient, for a listener who needs help. Donut reads bright and forward, for a viewer deciding whether to keep watching.
Is it suitable for long video?
The energy is written for short form. Across a long tutorial it starts to feel relentless, and Toast holds that distance in the same band.
Hear it read your own words. New accounts start with 100 free credits. Open the playground and this voice is already selected.
Start free