VITS (https://arxiv.org/abs/2106.06103) is a popular end-to-end (one-stage) TTS model.

Our hosted VITS TTS API features ultra-fast inference, the largest offering of languages (88) and the lowest price across all vendors.

Example

curl \
  -X POST \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_API_KEY" \
  -d '{
    "text": "The quick brown fox jumps over the lazy dog.",
    "voice_id": "vits-eng-1",
    "params": {
      "model": "vits",
      "speed": 1.1
    }
  }' \
  https://api.neets.ai/v1/tts > vits.mp3

Pricing

See our models page for pricing.

Voice IDs

Voice IDs for VITS have the following format: vits-{iso_code}-{speaker_id}

• iso_code is a three-letter ISO 639-3 code that represents the spoken language
• speaker_id is a positive integer used to distinguish between multiple speakers in one language

Our default English voice is vits-eng-1.

📘

Complete VITS Voice ID List

All 1,000+ voice IDs and samples for the vits model are listed here.

Supported Languages

See the table below for a complete list of supported languages and sample voice IDs: