Which script does it read?

Simplified Mandarin. Send the text as written; numbers and punctuation are read the way Mandarin speech says them.

Can it read Thai or English?

It reads both with a foreign accent, since the voice is designed around Mandarin. Thai narration wants Massaman, and English narration wants Espresso.

How is it different from Tao Huay?

Tao Huay is the tender female lead, close and a little sad. Oolong is the male narrator, lower and steadier, and it reads from outside the story.

All voices

Oolongอู่หลง

Low and smooth, the Mandarin voice that opens the story after dark.

Male · Mandarin Chinese · Magnetic narrator · 0:05oolong

0:05

夜深了，城市渐渐安静下来。今晚的故事，从一封迟到二十年的信开始。

The clip is a story's opening. Listen to the settle on 城市渐渐安静下来, and the weight the voice puts on 二十年.

Try it now All voices

Oolong reads Mandarin from the bottom of the male range with no edge on it. The pace is unhurried, the level is steady, and the pull is in the smoothness.

The register is the narrator of a late broadcast. It suits fiction, brand copy written to be admired, and a companion with some gravity, and it is too settled for a fast promo.

Cast it for#

Audio novels: Serialized fiction in Mandarin, read chapter after chapter.
Brand reads: Chinese brand and launch copy that has to sound considered.
Late-night storytelling: Radio-style narration and story podcasts in Mandarin.

Reach for instead

Tao Huay The same Mandarin register in a tender female voice.
Massaman The same low end in Thai.

In production#

Audio novels
Mandarin serialized fiction.
Advertising
Chinese brand and launch reads.
Podcasts
Mandarin story and narration podcasts.

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": "夜深了，城市渐渐安静下来。今晚的故事，从一封迟到二十年的信开始。",
    "voice": "oolong",
    "model": "paxa-tts-flash-v1"
  }' \
  --output oolong.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: "夜深了，城市渐渐安静下来。今晚的故事，从一封迟到二十年的信开始。",
    voice: "oolong",
    model: "paxa-tts-flash-v1",
  }),
});

if (!response.ok) throw new Error(`TTS failed: ${response.status}`);
await writeFile("oolong.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": "夜深了，城市渐渐安静下来。今晚的故事，从一封迟到二十年的信开始。", "voice": "oolong", "model": "paxa-tts-flash-v1"},
)
response.raise_for_status()

with open("oolong.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 11 minutes

API voice reference

Questions#

Which script does it read?: Simplified Mandarin. Send the text as written; numbers and punctuation are read the way Mandarin speech says them.
Can it read Thai or English?: It reads both with a foreign accent, since the voice is designed around Mandarin. Thai narration wants Massaman, and English narration wants Espresso.
How is it different from Tao Huay?: Tao Huay is the tender female lead, close and a little sad. Oolong is the male narrator, lower and steadier, and it reads from outside the story.

Hear it read your own words.

New accounts start with 100 free credits. Open the playground and this voice is already selected.

Start free Read the docs