src/docs/src/AI.md
The Puter.js AI feature allows you to integrate artificial intelligence capabilities into your applications.
You can use AI models from various providers to perform tasks such as chat, text-to-image, image-to-text, text-to-video, and text-to-speech conversion. And with the User-Pays Model, you don't have to set up your own API keys and top up credits, because users cover their own AI costs.
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat(`What is life?`, { model: "gpt-5.4-nano" }).then(puter.print);
</script>
</body>
</html>
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
// Generate an image of a cat using the default model and quality. Please note that testMode is set to true so that you can test this code without using up API credits.
puter.ai.txt2img('A picture of a cat.', true).then((image)=>{
document.body.appendChild(image);
});
</script>
</body>
</html>
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.img2txt('https://assets.puter.site/letter.png').then(puter.print);
</script>
</body>
</html>
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<button id="play">Speak!</button>
<script>
document.getElementById('play').addEventListener('click', ()=>{
puter.ai.txt2speech(`Hello world! Puter is pretty amazing, don't you agree?`).then((audio)=>{
audio.play();
});
});
</script>
</body>
</html>
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<button id="swap">Convert voice</button>
<script>
document.getElementById('swap').addEventListener('click', async ()=>{
const audio = await puter.ai.speech2speech(
'https://puter-sample-data.puter.site/tts_example.mp3',
{
voice: '21m00Tcm4TlvDq8ikWAM',
model: 'eleven_multilingual_sts_v2',
output_format: 'mp3_44100_128'
}
);
audio.play();
});
</script>
</body>
</html>
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.txt2vid(
"A drone shot sweeping over bioluminescent waves at night",
true // test mode returns a sample video without spending credits
).then((video)=>{
document.body.appendChild(video);
});
</script>
</body>
</html>
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.speech2speech('https://assets.puter.site/example.mp3', {
voice: '21m00Tcm4TlvDq8ikWAM',
model: 'eleven_multilingual_sts_v2',
output_format: 'mp3_44100_128'
}).then(puter.print);
</script>
</body>
</html>
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
(async () => {
const transcript = await puter.ai.speech2txt('https://assets.puter.site/example.mp3');
puter.print('Transcript:', transcript.text ?? transcript);
})();
</script>
</body>
</html>
These AI features are supported out of the box when using Puter.js:
puter.ai.chat() - Chat with AI models like Claude, GPT, and othersputer.ai.listModels() - List available AI chat models (and providers) that Puter currently exposes.puter.ai.txt2img() - Generate images from text descriptionsputer.ai.img2txt() - Extract text from images (OCR)puter.ai.txt2speech() - Convert text to speechputer.ai.txt2speech.listEngines() - List available TTS engines/modelsputer.ai.txt2speech.listVoices() - List available TTS voicesputer.ai.speech2speech() - Convert speech in one voice to another voiceputer.ai.txt2vid() - Generate short videos with OpenAI Sora modelsputer.ai.speech2txt() - Transcribe or translate audio recordings into textYou can see various Puter.js AI features in action from the following examples: