VITS

About VITS

VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is a fast, end-to-end neural TTS model that generates natural-sounding speech. It combines variational autoencoders with adversarial training for efficient synthesis. VITS is excellent for batch processing and applications requiring both quality and speed.

Key Features

Use Cases

How to Use VITS

1. 1

   Sign up free or try the demo

   Create a free TextToSpeechAI account to get starter credits, or use the on-page demo to hear VITS before signing up.

2. 2

   Pick a VITS voice or speaker

   Browse the voice library and choose a voice marked with the VITS badge. The multi-speaker VITS library, including the VCTK speaker set, lets you select from many distinct voices.

3. 3

   Enter your text

   Type or paste the text you want spoken into the editor. VITS handles long passages well and is ideal for batch and high-volume content.

4. 4

   Generate the audio

   Click generate to synthesize speech with VITS. Because VITS is very fast and Standard-tier (10 credits per 1000 characters), results return quickly at low cost.

5. 5

   Download or use the API

   Download the finished audio as MP3, WAV, or OGG, or call the same VITS voice through the TextToSpeechAI REST API to automate generation in your own application.

VITS API

Generate speech programmatically using the TextToSpeechAI REST API.

curl -X POST "https://api.texttospeechai.com/v1/generate/" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "VITS delivers fast, natural speech for high\u002Dvolume applications.",
    "voice": "vits-ljspeech"
  }'

Frequently Asked Questions