Zonos

About Zonos

Zonos by Zyphra is a 1.6B parameter text-to-speech model with advanced emotion and style control. It supports voice cloning from 5-30 seconds of reference audio and can modulate the emotional tone of generated speech. Choose from emotions like happiness, sadness, anger, fear, surprise, and disgust to create highly expressive and emotionally nuanced audio.

Key Features

Use Cases

How to Use Zonos

1. 1

   Sign up or open the demo

   Create a free TextToSpeechAI account to get starter credits, or use the no-signup demo to try Zonos right away.

2. 2

   Choose the Zonos engine

   Select Zonos from the voice and model picker. To clone a voice, upload 5-30 seconds of clean reference audio so Zonos can match the speaker.

3. 3

   Enter your text

   Type or paste the script you want spoken. Zonos works across English, Japanese, Chinese, French, and German.

4. 4

   Pick an emotion and generate

   Choose one of the seven Zonos emotions - neutral, happiness, sadness, anger, fear, surprise, or disgust - then click generate to render expressive speech in that mood.

5. 5

   Download or use the API

   Play back and download the finished audio, or call the same Zonos engine programmatically through the TextToSpeechAI REST API for automated workflows.

Zonos 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": "Zonos generates incredibly expressive speech with fine\u002Dgrained emotion control.",
    "voice": "en_US-lessac-medium"
  }'

Frequently Asked Questions