Text-to-Speech

Basic usage

Send a text input to generate an audio output:

import Bytez from "bytez.js";

const sdk = new Bytez("BYTEZ_KEY");
const model = sdk.model("suno/bark-small");

const { error, output } = await model.run("Hello, how are you today?");

console.log({ error, output });

Stream

Instead receiving an audio file in JSON format, you opt to stream back the data URL:

import Bytez from "bytez.js";

const sdk = new Bytez("BYTEZ_KEY");
const model = sdk.model("suno/bark-small");
const text = "Hello, how are you today?"
const stream = true

const readStream = await model.run(text, stream);

// the stream returns the base64 data url
for await (const chunk of readStream) {
  console.log(chunk)
}

Image Generation Text-to-Text Generation

Model API