stackadoc / stable-audio-open-1.0

Stable Audio Open is an open-source model optimized for generating short audio samples, sound effects, and production elements using text prompts.

Cold

Public
10.9K runs
L40S
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Prediction

stackadoc/stable-audio-open-1.0:49b1d4f06f69989dd2c8252d455d2deebaa3c3e3e894694b8aed301c69e75913

Model

stackadoc/stable-audio-open-1.0:49b1d4f0

8a171frdq5rgc0cg9b0s8vymkg

Status

Succeeded

Source

Web

Hardware

A100 (40GB)

Total duration

4m 16s

Created

11 months ago

Input

seed: -1
steps: 100
prompt: 128 BPM tech house drum loop
cfg_scale: 6
sigma_max: 500
sigma_min: 0.03
batch_size: 1
sampler_type: dpmpp-3m-sde
seconds_start: 0
seconds_total: 8
negative_prompt
init_noise_level: 1

{
  "seed": -1,
  "steps": 100,
  "prompt": "128 BPM tech house drum loop",
  "cfg_scale": 6,
  "sigma_max": 500,
  "sigma_min": 0.03,
  "batch_size": 1,
  "sampler_type": "dpmpp-3m-sde",
  "seconds_start": 0,
  "seconds_total": 8,
  "negative_prompt": "",
  "init_noise_level": 1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run stackadoc/stable-audio-open-1.0 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "stackadoc/stable-audio-open-1.0:49b1d4f06f69989dd2c8252d455d2deebaa3c3e3e894694b8aed301c69e75913",
  {
    input: {
      seed: -1,
      steps: 100,
      prompt: "128 BPM tech house drum loop",
      cfg_scale: 6,
      sigma_max: 500,
      sigma_min: 0.03,
      batch_size: 1,
      sampler_type: "dpmpp-3m-sde",
      seconds_start: 0,
      seconds_total: 8,
      negative_prompt: "",
      init_noise_level: 1
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run stackadoc/stable-audio-open-1.0 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stackadoc/stable-audio-open-1.0:49b1d4f06f69989dd2c8252d455d2deebaa3c3e3e894694b8aed301c69e75913",
    input={
        "seed": -1,
        "steps": 100,
        "prompt": "128 BPM tech house drum loop",
        "cfg_scale": 6,
        "sigma_max": 500,
        "sigma_min": 0.03,
        "batch_size": 1,
        "sampler_type": "dpmpp-3m-sde",
        "seconds_start": 0,
        "seconds_total": 8,
        "negative_prompt": "",
        "init_noise_level": 1
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run stackadoc/stable-audio-open-1.0 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "stackadoc/stable-audio-open-1.0:49b1d4f06f69989dd2c8252d455d2deebaa3c3e3e894694b8aed301c69e75913",
    "input": {
      "seed": -1,
      "steps": 100,
      "prompt": "128 BPM tech house drum loop",
      "cfg_scale": 6,
      "sigma_max": 500,
      "sigma_min": 0.03,
      "batch_size": 1,
      "sampler_type": "dpmpp-3m-sde",
      "seconds_start": 0,
      "seconds_total": 8,
      "negative_prompt": "",
      "init_noise_level": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

{
  "completed_at": "2024-06-24T15:02:20.169176Z",
  "created_at": "2024-06-24T14:58:04.345000Z",
  "data_removed": false,
  "error": null,
  "id": "8a171frdq5rgc0cg9b0s8vymkg",
  "input": {
    "seed": -1,
    "steps": 100,
    "prompt": "128 BPM tech house drum loop",
    "cfg_scale": 6,
    "sigma_max": 500,
    "sigma_min": 0.03,
    "batch_size": 1,
    "sampler_type": "dpmpp-3m-sde",
    "seconds_start": 0,
    "seconds_total": 8,
    "negative_prompt": "",
    "init_noise_level": 1
  },
  "logs": "Prompt: 128 BPM tech house drum loop\n630051780\n  0%|          | 0/100 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/backends/cuda/__init__.py:342: FutureWarning: torch.backends.cuda.sdp_kernel() is deprecated. In the future, this context manager will be removed. Please see, torch.nn.attention.sdpa_kernel() for the new context manager, with updated signature.\nwarnings.warn(\n  1%|          | 1/100 [00:00<00:28,  3.53it/s]\n  3%|▎         | 3/100 [00:00<00:12,  7.78it/s]\n  5%|▌         | 5/100 [00:00<00:09, 10.07it/s]\n  7%|▋         | 7/100 [00:00<00:08, 11.41it/s]\n  9%|▉         | 9/100 [00:00<00:07, 12.23it/s]\n 11%|█         | 11/100 [00:01<00:06, 12.81it/s]\n 13%|█▎        | 13/100 [00:01<00:06, 13.09it/s]\n 15%|█▌        | 15/100 [00:01<00:06, 13.32it/s]\n 17%|█▋        | 17/100 [00:01<00:06, 13.49it/s]\n 19%|█▉        | 19/100 [00:01<00:05, 13.62it/s]\n 21%|██        | 21/100 [00:01<00:05, 13.77it/s]\n 23%|██▎       | 23/100 [00:01<00:05, 13.92it/s]\n 25%|██▌       | 25/100 [00:02<00:05, 14.01it/s]\n 27%|██▋       | 27/100 [00:02<00:05, 13.97it/s]\n 29%|██▉       | 29/100 [00:02<00:05, 13.93it/s]\n 31%|███       | 31/100 [00:02<00:04, 13.95it/s]\n 33%|███▎      | 33/100 [00:02<00:04, 13.90it/s]\n 35%|███▌      | 35/100 [00:02<00:04, 13.89it/s]\n 37%|███▋      | 37/100 [00:02<00:04, 13.91it/s]\n 39%|███▉      | 39/100 [00:03<00:04, 13.95it/s]\n 41%|████      | 41/100 [00:03<00:04, 13.98it/s]\n 43%|████▎     | 43/100 [00:03<00:04, 14.01it/s]\n 45%|████▌     | 45/100 [00:03<00:03, 14.10it/s]\n 47%|████▋     | 47/100 [00:03<00:03, 14.17it/s]\n 49%|████▉     | 49/100 [00:03<00:03, 14.22it/s]\n 51%|█████     | 51/100 [00:03<00:03, 14.27it/s]\n 53%|█████▎    | 53/100 [00:03<00:03, 14.33it/s]\n 55%|█████▌    | 55/100 [00:04<00:03, 14.35it/s]\n 57%|█████▋    | 57/100 [00:04<00:02, 14.34it/s]\n 59%|█████▉    | 59/100 [00:04<00:02, 14.39it/s]\n 61%|██████    | 61/100 [00:04<00:02, 14.45it/s]\n 63%|██████▎   | 63/100 [00:04<00:02, 14.53it/s]\n 65%|██████▌   | 65/100 [00:04<00:02, 14.57it/s]\n 67%|██████▋   | 67/100 [00:04<00:02, 14.61it/s]\n 69%|██████▉   | 69/100 [00:05<00:02, 14.64it/s]\n 71%|███████   | 71/100 [00:05<00:01, 14.50it/s]\n 73%|███████▎  | 73/100 [00:05<00:01, 14.40it/s]\n 75%|███████▌  | 75/100 [00:05<00:01, 14.41it/s]\n 77%|███████▋  | 77/100 [00:05<00:01, 14.44it/s]\n 79%|███████▉  | 79/100 [00:05<00:01, 14.43it/s]\n 81%|████████  | 81/100 [00:05<00:01, 14.45it/s]\n 83%|████████▎ | 83/100 [00:06<00:01, 14.50it/s]\n 85%|████████▌ | 85/100 [00:06<00:01, 14.44it/s]\n 87%|████████▋ | 87/100 [00:06<00:00, 14.47it/s]\n 89%|████████▉ | 89/100 [00:06<00:00, 14.50it/s]\n 91%|█████████ | 91/100 [00:06<00:00, 14.57it/s]\n 93%|█████████▎| 93/100 [00:06<00:00, 14.64it/s]\n 95%|█████████▌| 95/100 [00:06<00:00, 14.71it/s]\n 97%|█████████▋| 97/100 [00:07<00:00, 14.79it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torchsde/_brownian/brownian_interval.py:599: UserWarning: Should have ta>=t0 but got ta=0.029999999329447746 and t0=0.03.\nwarnings.warn(f\"Should have ta>=t0 but got ta={ta} and t0={self._start}.\")\n 99%|█████████▉| 99/100 [00:07<00:00, 14.89it/s]\n100%|██████████| 100/100 [00:07<00:00, 13.86it/s]",
  "metrics": {
    "predict_time": 8.626604905,
    "total_time": 255.824176
  },
  "output": "https://replicate.delivery/czjl/Qcx1n6TxgkLAHV9FNyfNl0hRycNOfGR4IN3wG11bVRN8xzBTA/output.wav",
  "started_at": "2024-06-24T15:02:11.542571Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/8a171frdq5rgc0cg9b0s8vymkg",
    "cancel": "https://api.replicate.com/v1/predictions/8a171frdq5rgc0cg9b0s8vymkg/cancel"
  },
  "version": "49b1d4f06f69989dd2c8252d455d2deebaa3c3e3e894694b8aed301c69e75913"
}

Generated in

8.6 seconds

Tweak it Share Report

Prompt: 128 BPM tech house drum loop
630051780
  0%|          | 0/100 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/backends/cuda/__init__.py:342: FutureWarning: torch.backends.cuda.sdp_kernel() is deprecated. In the future, this context manager will be removed. Please see, torch.nn.attention.sdpa_kernel() for the new context manager, with updated signature.
warnings.warn(
  1%|          | 1/100 [00:00<00:28,  3.53it/s]
  3%|▎         | 3/100 [00:00<00:12,  7.78it/s]
  5%|▌         | 5/100 [00:00<00:09, 10.07it/s]
  7%|▋         | 7/100 [00:00<00:08, 11.41it/s]
  9%|▉         | 9/100 [00:00<00:07, 12.23it/s]
 11%|█         | 11/100 [00:01<00:06, 12.81it/s]
 13%|█▎        | 13/100 [00:01<00:06, 13.09it/s]
 15%|█▌        | 15/100 [00:01<00:06, 13.32it/s]
 17%|█▋        | 17/100 [00:01<00:06, 13.49it/s]
 19%|█▉        | 19/100 [00:01<00:05, 13.62it/s]
 21%|██        | 21/100 [00:01<00:05, 13.77it/s]
 23%|██▎       | 23/100 [00:01<00:05, 13.92it/s]
 25%|██▌       | 25/100 [00:02<00:05, 14.01it/s]
 27%|██▋       | 27/100 [00:02<00:05, 13.97it/s]
 29%|██▉       | 29/100 [00:02<00:05, 13.93it/s]
 31%|███       | 31/100 [00:02<00:04, 13.95it/s]
 33%|███▎      | 33/100 [00:02<00:04, 13.90it/s]
 35%|███▌      | 35/100 [00:02<00:04, 13.89it/s]
 37%|███▋      | 37/100 [00:02<00:04, 13.91it/s]
 39%|███▉      | 39/100 [00:03<00:04, 13.95it/s]
 41%|████      | 41/100 [00:03<00:04, 13.98it/s]
 43%|████▎     | 43/100 [00:03<00:04, 14.01it/s]
 45%|████▌     | 45/100 [00:03<00:03, 14.10it/s]
 47%|████▋     | 47/100 [00:03<00:03, 14.17it/s]
 49%|████▉     | 49/100 [00:03<00:03, 14.22it/s]
 51%|█████     | 51/100 [00:03<00:03, 14.27it/s]
 53%|█████▎    | 53/100 [00:03<00:03, 14.33it/s]
 55%|█████▌    | 55/100 [00:04<00:03, 14.35it/s]
 57%|█████▋    | 57/100 [00:04<00:02, 14.34it/s]
 59%|█████▉    | 59/100 [00:04<00:02, 14.39it/s]
 61%|██████    | 61/100 [00:04<00:02, 14.45it/s]
 63%|██████▎   | 63/100 [00:04<00:02, 14.53it/s]
 65%|██████▌   | 65/100 [00:04<00:02, 14.57it/s]
 67%|██████▋   | 67/100 [00:04<00:02, 14.61it/s]
 69%|██████▉   | 69/100 [00:05<00:02, 14.64it/s]
 71%|███████   | 71/100 [00:05<00:01, 14.50it/s]
 73%|███████▎  | 73/100 [00:05<00:01, 14.40it/s]
 75%|███████▌  | 75/100 [00:05<00:01, 14.41it/s]
 77%|███████▋  | 77/100 [00:05<00:01, 14.44it/s]
 79%|███████▉  | 79/100 [00:05<00:01, 14.43it/s]
 81%|████████  | 81/100 [00:05<00:01, 14.45it/s]
 83%|████████▎ | 83/100 [00:06<00:01, 14.50it/s]
 85%|████████▌ | 85/100 [00:06<00:01, 14.44it/s]
 87%|████████▋ | 87/100 [00:06<00:00, 14.47it/s]
 89%|████████▉ | 89/100 [00:06<00:00, 14.50it/s]
 91%|█████████ | 91/100 [00:06<00:00, 14.57it/s]
 93%|█████████▎| 93/100 [00:06<00:00, 14.64it/s]
 95%|█████████▌| 95/100 [00:06<00:00, 14.71it/s]
 97%|█████████▋| 97/100 [00:07<00:00, 14.79it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torchsde/_brownian/brownian_interval.py:599: UserWarning: Should have ta>=t0 but got ta=0.029999999329447746 and t0=0.03.
warnings.warn(f"Should have ta>=t0 but got ta={ta} and t0={self._start}.")
 99%|█████████▉| 99/100 [00:07<00:00, 14.89it/s]
100%|██████████| 100/100 [00:07<00:00, 13.86it/s]

Want to make some of these yourself?

Run this model