Media Generation

Synthome provides three generation functions for creating AI-generated media:

Function	Output	Use Case
`generateVideo()`	Video	Text-to-video, image-to-video
`generateImage()`	Image	Text-to-image, image editing
`generateAudio()`	Audio	Text-to-speech

Quick Examples

Generate a Video

import { compose, generateVideo, videoModel } from "@synthome/sdk";

const execution = await compose(
  generateVideo({
    model: videoModel("bytedance/seedance-1-pro", "replicate"),
    prompt: "A serene mountain landscape at sunrise",
    duration: 5,
  }),
).execute();

console.log(execution.result?.url);

Generate an Image

import { compose, generateImage, imageModel } from "@synthome/sdk";

const execution = await compose(
  generateImage({
    model: imageModel("google/nano-banana", "fal"),
    prompt: "A futuristic city skyline at night",
  }),
).execute();

console.log(execution.result?.url);

Generate Audio

import { compose, generateAudio, audioModel } from "@synthome/sdk";

const execution = await compose(
  generateAudio({
    model: audioModel("elevenlabs/turbo-v2.5", "elevenlabs"),
    text: "Welcome to Synthome, the composable AI media toolkit.",
    voiceId: "EXAVITQu4vr4xnSDxMaL",
  }),
).execute();

console.log(execution.result?.url);

Nested Generation

Generation functions can be nested inside each other. For example, generate an image and use it as input for video generation:

const execution = await compose(
  generateVideo({
    model: videoModel("bytedance/seedance-1-pro", "replicate"),
    prompt: "Make this scene come alive with gentle movement",
    image: generateImage({
      model: imageModel("google/nano-banana", "fal"),
      prompt: "A peaceful Japanese garden with cherry blossoms",
    }),
  }),
).execute();

The image is generated first, then passed to the video model automatically.

Using URLs

All generation functions that accept media inputs also accept direct URLs:

// Use an existing image URL for video generation
generateVideo({
  model: videoModel("bytedance/seedance-1-pro", "replicate"),
  prompt: "Animate this image",
  image: "https://example.com/my-image.jpg",
});

// Use an existing audio URL
generateVideo({
  model: videoModel("veed/fabric-1.0", "fal"),
  prompt: "Lip sync to this audio",
  image: "https://example.com/portrait.jpg",
  audio: "https://example.com/speech.mp3",
});