
Toastโทสต์
The voice of someone showing you how, at the speed you can follow.
Male · English · Tutorials · 0:04toast
In this tutorial, we'll set up the project step by step, starting with the basics.
The clip is a tutorial open. Listen to the even weight on step by step, which sets the pace for everything after it.
Toast reads English the way a colleague explains a process. There is no announcer polish on it, and the plainness is what keeps a viewer with a long tutorial to the end.
The register handles distance. Where the promo voices are written for thirty seconds, this one is built for the twenty minutes it takes to actually build something.
Cast it for#
- Tutorials and walkthroughs
- Long instructional video where the viewer is following along.
- Documentation audio
- Guides and references read aloud, where clarity outranks personality.
- Course narration
- English lessons and modules that a learner replays.
Reach for instead
In production#
- E-learning
English course and module narration.
- Accessibility
Documentation and guides read aloud.
- Creators
Long-form instructional video.
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": "In this tutorial, we'll set up the project step by step, starting with the basics.",
"voice": "toast",
"model": "paxa-tts-flash-v1"
}' \
--output toast.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: "In this tutorial, we'll set up the project step by step, starting with the basics.",
voice: "toast",
model: "paxa-tts-flash-v1",
}),
});
if (!response.ok) throw new Error(`TTS failed: ${response.status}`);
await writeFile("toast.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": "In this tutorial, we'll set up the project step by step, starting with the basics.", "voice": "toast", "model": "paxa-tts-flash-v1"},
)
response.raise_for_status()
with open("toast.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#
- Does it work for long video?
- That is the distance it is built for. The register stays plain enough to follow for twenty minutes, where a promo read would wear out in two.
- Can it read Thai?
- It reads Thai with a foreign accent, since the voice is designed around English. Thai tutorials want Tako or Foi Thong, both of which read English terms inside Thai lines.
- How does it handle code and technical terms?
- Technical English reads as written. Sending a term the way you want it heard is the reliable approach, since the voice reads the text it is given.
Hear it read your own words.
New accounts start with 100 free credits. Open the playground and this voice is already selected.