Instructions to use sammoran-phd/cara-native-stable-audio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Stable Audio Tools
How to use sammoran-phd/cara-native-stable-audio with Stable Audio Tools:
import torch import torchaudio from einops import rearrange from stable_audio_tools import get_pretrained_model from stable_audio_tools.inference.generation import generate_diffusion_cond device = "cuda" if torch.cuda.is_available() else "cpu" # Download model model, model_config = get_pretrained_model("sammoran-phd/cara-native-stable-audio") sample_rate = model_config["sample_rate"] sample_size = model_config["sample_size"] model = model.to(device) # Set up text and timing conditioning conditioning = [{ "prompt": "128 BPM tech house drum loop", }] # Generate stereo audio output = generate_diffusion_cond( model, conditioning=conditioning, sample_size=sample_size, device=device ) # Rearrange audio batch to a single sequence output = rearrange(output, "b d n -> d (b n)") # Peak normalize, clip, convert to int16, and save to file output = output.to(torch.float32).div(torch.max(torch.abs(output))).clamp(-1, 1).mul(32767).to(torch.int16).cpu() torchaudio.save("output.wav", output, sample_rate) - Notebooks
- Google Colab
- Kaggle
| { | |
| "status": "completed", | |
| "run_id": "run_000002", | |
| "started_at": "2026-05-21T11:51:50.241886+00:00", | |
| "finished_at": "2026-05-21T11:52:17.350325+00:00", | |
| "updated_at": "2026-05-21T11:52:17.350325+00:00", | |
| "current_phase": "completed", | |
| "current_asset": null, | |
| "current_asset_title": null, | |
| "current_pool_id": null, | |
| "processed_assets": 25000, | |
| "total_assets": 25000, | |
| "percent_complete": 100.0, | |
| "counts": { | |
| "review_required": 727, | |
| "new_pool_created": 98, | |
| "assigned": 24175, | |
| "duplicate_found": 0, | |
| "rejected": 0, | |
| "unresolved": 0 | |
| }, | |
| "options": { | |
| "subset_role": "music_train_candidate", | |
| "only_downloaded": true, | |
| "limit": null, | |
| "allow_relaxed_metadata": true, | |
| "start_fresh": true | |
| }, | |
| "activity_log": [ | |
| { | |
| "ts": "2026-05-21T11:51:50.241979+00:00", | |
| "phase": "planning", | |
| "level": "info", | |
| "asset_id": null, | |
| "source_key": null, | |
| "pool_id": null, | |
| "message": "v2 planning run started for 25000 candidate assets" | |
| }, | |
| { | |
| "ts": "2026-05-21T11:52:13.536231+00:00", | |
| "phase": "planning", | |
| "level": "info", | |
| "asset_id": null, | |
| "source_key": null, | |
| "pool_id": null, | |
| "message": "v2 normalized 25000 assets; building broad pool map" | |
| }, | |
| { | |
| "ts": "2026-05-21T11:53:07.604214+00:00", | |
| "phase": "completed", | |
| "level": "info", | |
| "asset_id": null, | |
| "source_key": null, | |
| "pool_id": null, | |
| "message": "v2 completed: 24273 training rows across 98 registered pools" | |
| } | |
| ] | |
| } |