Text to Speech

Turn text into natural speech with a project-scoped API key.

TRY ITExperience Center

Type text, choose a voice, and hear the result without writing code.

GET STARTEDQuickstart

Create an API key and save your first generated audio file.

REFERENCEAPI details

Review endpoints, request fields, and response handling.

When to use it

Voiceovers and narrationProduct demos, videos, stories, and long-form content.

Conversational experiencesTurn an assistant response into audio or stream it as it is generated.

Accessibility and IVRRead content aloud, build phone menus, and create spoken guidance.

Product notificationsGenerate alerts, status updates, and personalized messages.

Quick start

Set the API address and key before running an example. See Get your API key if you do not have one yet.

export VUILABS_API_BASE_URL="https://api-global.vuilabs.ai"
export VUILABS_API_KEY="your-api-key"

cURL

curl --request POST \
  --url "$VUILABS_API_BASE_URL/v1/text-to-speech" \
  --header "X-API-Key: $VUILABS_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "generate_text": "Your order is ready.",
    "language": "en",
    "speed": 1
  }' \
  --output speech.mp3

JavaScript

import { writeFile } from 'node:fs/promises';

const response = await fetch(`${process.env.VUILABS_API_BASE_URL}/v1/text-to-speech`, {
  method: 'POST',
  headers: {
    'X-API-Key': process.env.VUILABS_API_KEY,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({ generate_text: 'Your order is ready.', language: 'en', speed: 1 }),
});

if (!response.ok) throw new Error(await response.text());
await writeFile('speech.mp3', Buffer.from(await response.arrayBuffer()));

Python

import os
import requests

response = requests.post(
    f"{os.environ['VUILABS_API_BASE_URL']}/v1/text-to-speech",
    headers={"X-API-Key": os.environ["VUILABS_API_KEY"]},
    json={"generate_text": "Your order is ready.", "language": "en", "speed": 1},
)
response.raise_for_status()

with open("speech.mp3", "wb") as output:
    output.write(response.content)

Use a specific voice

Set voice_id to a voice enabled for your project. Start with a short representative sentence before generating longer content.

cURL

curl --request POST \
  --url "$VUILABS_API_BASE_URL/v1/text-to-speech" \
  --header "X-API-Key: $VUILABS_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "generate_text": "This request uses a specific voice.",
    "voice_id": "your-approved-voice-id",
    "language": "en",
    "speed": 1
  }' \
  --output speech.mp3

JavaScript

import { writeFile } from 'node:fs/promises';

const response = await fetch(`${process.env.VUILABS_API_BASE_URL}/v1/text-to-speech`, {
  method: 'POST',
  headers: {
    'X-API-Key': process.env.VUILABS_API_KEY,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    generate_text: 'This request uses a specific voice.',
    voice_id: 'your-approved-voice-id',
    language: 'en',
    speed: 1,
  }),
});

if (!response.ok) throw new Error(await response.text());
await writeFile('speech.mp3', Buffer.from(await response.arrayBuffer()));

Python

import os
import requests

response = requests.post(
    f"{os.environ['VUILABS_API_BASE_URL']}/v1/text-to-speech",
    headers={"X-API-Key": os.environ["VUILABS_API_KEY"]},
    json={
        "generate_text": "This request uses a specific voice.",
        "voice_id": "your-approved-voice-id",
        "language": "en",
        "speed": 1,
    },
)
response.raise_for_status()

with open("speech.mp3", "wb") as output:
    output.write(response.content)

API details

Request modes

COMPLETE AUDIOPOST /v1/text-to-speech

Wait for the complete audio response before playback or storage.

STREAMING AUDIOPOST /v1/text-to-speech/stream

Consume raw audio bytes as they become available.

Both endpoints use X-API-Key. The key determines the project, allowed capability, rate limit, and billing account.

Request headers

Header	Required	Description
X-API-Key	Yes	Your project API key.
Content-Type	Yes	application/json

JSON body

Field	Type	Required	Use it for
generate_text	string	Yes	The text to synthesize. Billing uses weighted character count.
language	string	No	A language enabled for your TTS account.
voice_id	string	No	An approved voice. Omit to use the configured default voice.
speed	number	No	Delivery speed. Omit or use 0 for the provider default; negative values are rejected.
emotion_class	string	No	An approved emotion preset, when supported by the selected voice.
audio_format	string	No	An output format enabled for the selected voice and request mode.

Streaming generation

The synchronous endpoint returns the complete file. The streaming endpoint returns HTTP chunked raw audio bytes in order; it is not SSE or a JSON event stream.

Handle the response as audio

For both endpoints, HTTP 200 means the response body is audio, not JSON. The response Content-Type is the actual audio MIME type returned by the approved provider.