🎵 Stable Audio 3 Medium — Music API

Text-to-music via stabilityai/stable-audio-3-medium (general audio, the largest SA3 variant), proxied from stabilityai/stable-audio-3.

Bring your own token. This Space stores no credentials — it forwards the hf_token you pass straight to upstream, so the ZeroGPU quota is charged to you. A plain read token is enough.

from gradio_client import Client

client = Client("sleeper371/stable-audio-3-medium-api")
wav_path, status = client.predict(
    prompt="Warm analog house groove, deep sub bass, shuffled hats 122 BPM",
    duration=30,
    hf_token="hf_...",      # your token — your quota
    api_name="/generate",
)