MAGNeT
MAGNeT is Meta's masked, non-autoregressive audio generator. Instead of predicting tokens left to right it fills masked audio tokens in parallel over a few decoding steps, so generation is faster than autoregressive MusicGen at similar quality. This Replicate packaging exposes the text-to-music and text-to-sound variants.
MAGNeT is audio & music AI model from Community, priced at €0.000 per 1M input tokens with a unknown context window.
About this model
Pricing
API Integration
Use our OpenAI-compatible API to integrate MAGNeT into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple — just pass a string
const reply = await rw.run("magnet", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("magnet", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("magnet", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Frequently asked questions
Related Models
View all Audio & MusicMusicGen
Meta's music generation model. Generate up to 1 minute of music from text descriptions.
Bark
Suno's text-to-audio model. Generates realistic speech, music, and sound effects.
Stable Audio Open 1.0
Stability AI's Stable Audio Open generates short audio from text prompts, tuned for sound effects, drum loops, instrument riffs and production elements rather than full songs. Open weights, latent diffusion over a 44.1kHz audio autoencoder, with a configurable seconds_total up to about 47 seconds.
Udio V1.5
AI music generation with studio-quality output. Generate full songs with vocals, instruments, and production.
Start using MAGNeT today
Get started with free credits. No credit card required. Access MAGNeT and 100+ other models through a single API.