All models

MusicGen

Write music from a description, a melody, or both

Generate Audiov1.0.08 inputsAUDIO

a slow acoustic guitar melody over soft brushed drums

Try it right here

Fill the inputs the node publishes and run it on your own account. The same ports, defaults and types the studio uses.

Inputs

TEXT
TEXT
Model
1 – 300INT
Duration (seconds)
AUDIO
Melody or clip to continue
BOOLEAN
Continue the clip
0 – 2FLOAT
TEXT
INT
Sign in to run

Running a model executes it on your account. Browsing the catalog stays free and needs no account.

Output

Fill in the inputs and run the node to see its output here.

Call it from your code

The same node, called by id from any surface. Every tab pins this node and passes the ports below.

import { BlitClient } from "@blitflow/sdk";

const { runNode } = new BlitClient({ apiKey: process.env.BLITFLOW_TOKEN });

const { outputs } = await runNode("musicgen", {
  prompt: { value: "example" },
  modelVersion: { value: "stereo-melody-large" },
  duration: { value: 8 },
  melody: { ref: "https://..." },
  continuation: { value: false },
  temperature: { value: 1 },
  outputFormat: { value: "mp3" },
  seed: { value: 1 },
});

Schema

Every port this node publishes, with its type, its hint and the default it runs with. musicgen is the id you call.

Inputs

prompt*TEXT
modelVersionTEXT
Model
stereo-melody-large · stereo-large · melody-large · large
stereo-melody-large
durationINT
Duration (seconds)
8
melodyAUDIO
Melody or clip to continue
continuationBOOLEAN
Continue the clip
false
temperatureFLOAT1
outputFormatTEXT
wav · mp3
mp3
seedINT

Outputs

audioAUDIO

Chain it with the rest of the catalog

Open the studio