Tortoise TTS

About Tortoise TTS

Tortoise TTS is an autoregressive text-to-speech model that prioritizes audio quality above all else. Using a combination of autoregressive transformers and diffusion models, Tortoise generates extremely natural speech that captures subtle nuances of human voice. While slower than other models, Tortoise produces the most natural-sounding TTS output available.

Key Features

Use Cases

How to Use Tortoise TTS

1. 1

   Sign up free

   Create a free TextToSpeechAI account to get starter credits. Tortoise is an Ultra-tier engine (50 credits per 1000 characters), so the free credits are perfect for a first short test.

2. 2

   Choose a Tortoise voice

   Select one of the built-in Tortoise voices from the voice browser.

3. 3

   Enter your text

   Type or paste the text you want narrated. Because Tortoise is slow, start with a short passage to confirm the voice and tone before sending a full audiobook chapter or long script.

4. 4

   Generate

   Click generate and be patient. Tortoise can take from 30 seconds to several minutes per clip.

5. 5

   Download or use the API

   When generation finishes, download your audio as MP3, WAV, or OGG, or fetch it from your history. To automate Tortoise jobs, call the TextToSpeechAI API and allow longer timeouts, since Tortoise renders slowly.

Tortoise TTS 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": "Tortoise takes its time, but the results are worth waiting for.",
    "voice": "tortoise-angie"
  }'

Frequently Asked Questions