Qwen 3 TTS 12Hz 1.7B qwen3-tts-12hz-1.7b

Text-to-speech in 10 languages with built-in speakers, voice design, and voice cloning.

From the live catalog

Speech

$0.00028 / second

region ATL Hugging Face Qwen/Qwen3-TTS-12Hz-1.7B-Base

Inputs

Input	Accepts
`text`	max prompt 6,000 characters

Parameters

Streams with stream: true.

Parameter	Type	Values	Default
`voice`	string	vivian, serena, uncle_fu, dylan, eric, ryan, aiden, ono_anna, sohee, design, clone
`instructions`	any
`language`	any
`input_references`	array	up to 2 items
`response_format`	string	mp3, opus, flac, wav, pcm	`mp3`
`stream_format`	string	audio, sse	`audio`
`speed`	number	0.25–4	`1`
`seed`	integer
`temperature`	number	0–2
`top_p`	number	0–1
`top_k`	integer

Endpoints

POST/v1/audio/speech Create Speech

A request

curl https://api.vultrinference.com/v1/audio/speech \
  -H "Authorization: Bearer $VULTR_INFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-tts-12hz-1.7b",
    "input": "Welcome to Vultr Serverless Inference.",
    "voice": "aiden",
    "instructions": "Warm and upbeat, like a radio host."
  }'

import os
import requests

response = requests.post(
    "https://api.vultrinference.com/v1/audio/speech",
    headers={"Authorization": f"Bearer {os.environ['VULTR_INFERENCE_API_KEY']}"},
    json={
        "model": "qwen3-tts-12hz-1.7b",
        "input": "Welcome to Vultr Serverless Inference.",
        "voice": "aiden",
        "instructions": "Warm and upbeat, like a radio host.",
    },
)
print(response.status_code)

const response = await fetch("https://api.vultrinference.com/v1/audio/speech", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VULTR_INFERENCE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "qwen3-tts-12hz-1.7b",
    "input": "Welcome to Vultr Serverless Inference.",
    "voice": "aiden",
    "instructions": "Warm and upbeat, like a radio host."
  }),
});
console.log(response.status);