Generate speech in 5 minutes

Before you start

Create a project and an API key before making a request. See Get your API key for the complete steps.

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

Before running the request, replace YOUR_PROJECT_VOICE_ID with a voice available to this API key. It is not a shared demo voice; for a cloned voice, create it first with the Voice Cloning API.

Keep your key safe

Never share your API key or add it to public source code.

Generate your first audio

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 '{
    "text": "Hello from VUILabs.",
    "voice_id": "YOUR_PROJECT_VOICE_ID",
    "language": "en",
    "speed": 1
  }' \
  --output speech.wav

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({
    text: 'Hello from VUILabs.',
    voice_id: 'YOUR_PROJECT_VOICE_ID',
    language: 'en',
    speed: 1,
  }),
});

if (!response.ok) throw new Error(await response.text());
await writeFile('speech.wav', 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={"text": "Hello from VUILabs.", "voice_id": "YOUR_PROJECT_VOICE_ID", "language": "en", "speed": 1},
)
response.raise_for_status()

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

What happens next

The API returns raw audio bytes in an HTTP 200 response. Save the response to a file or pass it directly to an audio player.

✓

Need to specify a voice? Choose a voice_id enabled for the current project.

✓

Need the first audio chunk sooner? Switch to the streaming endpoint.

✓

Need a different audio format? Both complete and Luna-TTS streaming requests support WAV (default) or raw PCM. Send audio_format: "pcm" for PCM and read the response audio metadata before playback.

Continue to Voices and output, or see the full Text to Speech API reference.