Kokoro

About Kokoro

Kokoro is an ultra-lightweight 82M parameter TTS model that delivers natural-sounding speech at incredible speed. It runs near real-time even on CPU, making it ideal for applications where low latency is critical. Kokoro supports multiple languages and offers voice blending capabilities.

Key Features

Use Cases

How to Use Kokoro

1. 1

   Sign up free or try the demo

   Create a free TextToSpeechAI account to get 200 starter credits, or use the no-signup demo to hear Kokoro instantly. The standard tier means Kokoro only costs 10 credits per 1000 characters.

2. 2

   Pick a Kokoro voice

   Open the voice browser and select a Kokoro voice in your target language (9 supported, from English to Japanese and Korean). You can also use Kokoro voice blending to mix two voices into a custom combination.

3. 3

   Enter your text

   Type or paste the text you want spoken into the editor. Kokoro handles long passages efficiently thanks to its lightweight 82M-parameter, near real-time engine.

4. 4

   Adjust speed and generate

   Set the playback speed to suit your use case, then click Generate. Kokoro renders audio faster than real-time, so your speech is ready almost immediately.

5. 5

   Download or use the API

   Download the finished audio as MP3 or WAV, or automate generation through the TextToSpeechAI REST API at api.texttospeechai.com for batch and real-time workloads.

Kokoro 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": "Kokoro delivers natural speech with incredible speed and efficiency.",
    "voice": "en_US-lessac-medium"
  }'

Frequently Asked Questions