stable-audio

This documentation is valid for the following list of our models:

stable-audio

Try in Playground

An advanced audio generation model designed to create high-quality audio tracks from textual prompts.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schemas

post

Body

modelstring · enumRequiredPossible values:

promptstringRequired

The prompt to generate audio.

seconds_startinteger · min: 1 · max: 47Optional

The start point of the audio clip to generate.

seconds_totalinteger · min: 1 · max: 47Optional

The duration of the audio clip to generate.

Default: 30

stepsinteger · min: 1 · max: 1000Optional

The number of steps to denoise the audio.

Default: 100

Responses

200Success

application/json

post

/v2/generate/audio

async function main() {
  const response = await fetch('https://api.aimlapi.com/v2/generate/audio', {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      "model": "stable-audio",
      "prompt": "lo-fi pop hip-hop ambient music, slow intro: 10 s, then faster and with loud bass: 10 s",
      "seconds_total": 20
    }),
  });

  const data = await response.json();
  console.log(JSON.stringify(data, null, 2));
}

main();

200Success

{
  "id": "60ac7c34-3224-4b14-8e7d-0aa0db708325",
  "status": "completed",
  "audio_file": {
    "url": "https://cdn.aimlapi.com/generations/hippopotamus/1757963033314-8ca7729d-b78c-4d4c-9ef9-89b2fb3d07e8.mp3"
  },
  "error": {
    "name": "text",
    "message": "text"
  },
  "meta": {
    "usage": {
      "credits_used": 120000
    }
  }
}

Retrieve the generated music sample from the server

After sending a request for music generation, this task is added to the queue. Based on the service's load, the generation can be completed in 30-40 seconds or take a bit more.

get

Authorizations

AuthorizationstringRequired

Bearer key

Query parameters

generation_idstringRequired

Responses

default

application/json

get

/v2/generate/audio

GET /v2/generate/audio?generation_id=text HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer YOUR_SECRET_TOKEN
Accept: */*

default

{
  "audio_file": {
    "url": "https://example.com"
  },
  "id": "text",
  "status": "queued",
  "error": null
}

Full Example: Generating and Retrieving the Audio From the Server

The code below creates a audio generation task, then automatically polls the server every 10 seconds until it finally receives the video URL.

import time
import requests

# Insert your AI/ML API key instead of <YOUR_AIMLAPI_KEY>:
aimlapi_key = '<YOUR_AIMLAPI_KEY>'

# Creating and sending an audio generation task to the server (returns a generation ID)
def generate_audio():
    url = "https://api.aimlapi.com/v2/generate/audio"
    payload = {
        "model": "elevenlabs/eleven_music",
        "prompt": "lo-fi pop hip-hop ambient music, slow intro: 10 s, then faster and with loud bass: 10 s",
        "seconds_total": 20,
    }
    headers = {"Authorization": f"Bearer {aimlapi_key}", "Content-Type": "application/json"}

    response = requests.post(url, json=payload, headers=headers)

    if response.status_code >= 400:
        print(f"Error: {response.status_code} - {response.text}")
    else:
        response_data = response.json()
        print("Generation: ", response_data)
        return response_data


# Requesting the result of the generation task from the server using the generation_id:
def retrieve_audio(gen_id):
    url = "https://api.aimlapi.com/v2/generate/audio"
    params = {
        "generation_id": gen_id,
    }
    headers = {"Authorization": f"Bearer {aimlapi_key}", "Content-Type": "application/json"}
    response = requests.get(url, params=params, headers=headers)
    return response.json()
    
# This is the main function of the program. From here, we sequentially call the audio generation and then repeatedly request the result from the server every 10 seconds:
def main():
    generation_response = generate_audio()
    gen_id = generation_response.get("id")
        
    if gen_id:
        start_time = time.time()

        timeout = 600
        while time.time() - start_time < timeout:
            response_data = retrieve_audio(gen_id)

            if response_data is None:
                print("Error: No response from API")
                break
        
            status = response_data.get("status")
            
            if status in ["waiting", "queued", "generating"]:
                print(f"Status: {status}. Checking again in 10 seconds.")
                time.sleep(10)
            else:
                print("Generation complete:/n", response_data)
                return response_data
   
        print("Timeout reached. Stopping.")
        return None
        

if __name__ == "__main__":
    main()

const https = require("https");
const { URL } = require("url");

// Replace <YOUR_AIMLAPI_KEY> with your actual AI/ML API key
const apiKey = "<YOUR_AIMLAPI_KEY>";
const baseUrl = "https://api.aimlapi.com/v2";

// Creating and sending a audio generation task to the server
function generateAudio(callback) {
  const data = JSON.stringify({
      model: "elevenlabs/eleven_music",
      prompt: "lo-fi pop hip-hop ambient music, slow intro: 10 s, then faster and with loud bass: 10 s",
      seconds_total: 20,
  });

  const url = new URL(`${baseUrl}/generate/audio`);
  const options = {
    method: "POST",
    headers: {
      "Authorization": `Bearer ${apiKey}`,
      "Content-Type": "application/json",
      "Content-Length": Buffer.byteLength(data),
    },
  };

  const req = https.request(url, options, (res) => {
    let body = "";
    res.on("data", (chunk) => body += chunk);
    res.on("end", () => {
      if (res.statusCode >= 400) {
        console.error(`Error: ${res.statusCode} - ${body}`);
        callback(null);
      } else {
        const parsed = JSON.parse(body);
        callback(parsed);
      }
    });
  });

  req.on("error", (err) => console.error("Request error:", err));
  req.write(data);
  req.end();
}

// Requesting the result of the task from the server using the generation_id
function getAudio(genId, callback) {
  const url = new URL(`${baseUrl}/generate/audio`);
  url.searchParams.append("generation_id", genId);

  const options = {
    method: "GET",
    headers: {
      "Authorization": `Bearer ${apiKey}`,
      "Content-Type": "application/json",
    },
  };

  const req = https.request(url, options, (res) => {
    let body = "";
    res.on("data", (chunk) => body += chunk);
    res.on("end", () => {
      const parsed = JSON.parse(body);
      callback(parsed);
    });
  });

  req.on("error", (err) => console.error("Request error:", err));
  req.end();
}

// Initiates sound generation and checks the status every 10 seconds until completion or timeout
function main() {
    generateAudio((genResponse) => {
        if (!genResponse || !genResponse.id) {
            console.error("No generation ID received.");
            return;
        }

        const genId = genResponse.id;
        console.log("Generation ID:", genId);

        const timeout = 1000 * 1000; // 1000 sec
        const interval = 10 * 1000; // 10 sec
        const startTime = Date.now();

        const checkStatus = () => {
            if (Date.now() - startTime >= timeout) {
                console.log("Timeout reached. Stopping.");
                return;
            }

            getAudio(genId, (responseData) => {
                if (!responseData) {
                    console.error("Error: No response from API");
                    return;
                }

                const status = responseData.status;
        
                if (["waiting", "queued", "generating"].includes(status)) {
                    console.log(`Status: ${status}. Checking again in 10 seconds.`);
                    setTimeout(checkStatus, interval);
                } else {
                    console.log("Processing complete:\n", responseData);
                }
            });
        };
        checkStatus();
    })
}

main();

Response

Generation ID: ed58c4e0-2ed6-429f-91a1-b2c13a89ff46:stable-audio
Status: queued. Checking again in 10 seconds.
Status: generating. Checking again in 10 seconds.
Status: generating. Checking again in 10 seconds.
Status: generating. Checking again in 10 seconds.
Processing complete:
 {
  id: 'ed58c4e0-2ed6-429f-91a1-b2c13a89ff46:stable-audio',
  status: 'completed',
  audio_file: {
    url: 'https://cdn.aimlapi.com/flamingo/files/b/0a88448e/wxI96EIL4Noe21Zt3XsFc_tmpdwdfh537.wav',
    content_type: 'application/octet-stream',
    file_name: 'tmpdwdfh537.wav',
    file_size: 5292078
  }
}

Listen to the track we generated:

PreviousStability AI NextVoice/Speech Models

Last updated 1 day ago

Was this helpful?