music-01

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

music-01

An advanced AI model that generates diverse high-quality audio compositions by analyzing and reproducing musical patterns, rhythms, and vocal styles from the reference track. Refine the process using a text prompt.

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.

Quick Code Example

Here is an example of generation an audio file based on a sample and a prompt using the music model music-01.

import requests

# Insert your AI/ML API key here:
aimlapi_key = "<YOUR_AIMLAPI_KEY>"

# Input data
audio_url = "https://tand-dev.github.io/audio-hosting/spinning-head-271171.mp3"
file_name = "spinning-head-271171.mp3"
purpose = "song"  # Possible values: 'song', 'voice', 'instrumental'


def upload_reference_file():
    """Download file from URL and upload it to AIML API"""

    url = "https://api.aimlapi.com/v2/generate/audio/minimax/upload"

    try:
        # Step 1: Download the file
        response = requests.get(audio_url)
        response.raise_for_status()

        # Step 2: Upload to AIML API
        payload = {"purpose": purpose}
        files = {"file": (file_name, response.content, "audio/mpeg")}
        headers = {"Authorization": f"Bearer {aimlapi_key}"}

        upload_response = requests.post(url, headers=headers, files=files, data=payload)
        upload_response.raise_for_status()

        data = upload_response.json()
        print("Upload successful:", data)
        return data  # return JSON with file ids

    except requests.exceptions.RequestException as error:
        print(f"Error during upload: {error}")
        return None


def generate_audio(voice_id=None, instrumental_id=None):
    """Send audio generation request and save result"""

    url = "https://api.aimlapi.com/v2/generate/audio/minimax/generate"
    lyrics = (
        "##Side by side, through thick and thin, \n\n"
        "With a laugh, we always win. \n\n"
        "Storms may come, but we stay true, \n\n"
        "Friends forever—me and you!##"
    )

    payload = {
        "refer_voice": voice_id,
        "refer_instrumental": instrumental_id,
        "lyrics": lyrics,
        "model": "music-01",
    }
    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {aimlapi_key}",
    }

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

    audio_hex = response.json()["data"]["audio"]
    decoded_hex = bytes.fromhex(audio_hex)

    out_name = "generated_audio.mp3"
    with open(out_name, "wb") as f:
        f.write(decoded_hex)

    print(f"Generated audio saved as {out_name}")


def main():
    uploaded = upload_reference_file()
    if not uploaded:
        return

    # Extract IDs depending on purpose
    voice_id = uploaded.get("voice_id")
    instrumental_id = uploaded.get("instrumental_id")

    generate_audio(voice_id, instrumental_id)


if __name__ == "__main__":
    main()

import { writeFile } from "node:fs/promises";
import { Blob } from "node:buffer";

// Insert your AI/ML API key here:
const API_KEY = "<YOUR_AIMLAPI_KEY>";

// Input data
const AUDIO_URL = "https://tand-dev.github.io/audio-hosting/spinning-head-271171.mp3";
const FILE_NAME = "spinning-head-271171.mp3";
const PURPOSE = "song"; // Possible values: 'song', 'voice', 'instrumental'

// Download file from URL and upload it to AIML API
async function uploadReferenceFile() {
  const uploadUrl = "https://api.aimlapi.com/v2/generate/audio/minimax/upload";

  try {
    // Step 1: Download the file
    const response = await fetch(AUDIO_URL);
    if (!response.ok) throw new Error(`Failed to download file: ${response.status}`);

    const arrayBuffer = await response.arrayBuffer();
    const fileBlob = new Blob([arrayBuffer], { type: "audio/mpeg" });

    // Step 2: Upload to AIML API
    const formData = new FormData();
    formData.append("purpose", PURPOSE);
    formData.append("file", fileBlob, FILE_NAME);

    const uploadResponse = await fetch(uploadUrl, {
      method: "POST",
      headers: {
        Authorization: `Bearer ${API_KEY}`,
        // Content-Type should not be set manually for FormData
      },
      body: formData,
    });

    if (!uploadResponse.ok) {
      const text = await uploadResponse.text();
      throw new Error(`Upload failed ${uploadResponse.status}: ${text}`);
    }

    const data = await uploadResponse.json();
    console.log("Upload successful:", data);
    return data; // JSON with file ids

  } catch (err) {
    console.error("Error during upload:", err.message);
    return null;
  }
}

// Send audio generation request and save result
async function generateAudio(voiceId = null, instrumentalId = null) {
  const url = "https://api.aimlapi.com/v2/generate/audio/minimax/generate";
  const lyrics = `
##Side by side, through thick and thin,
With a laugh, we always win.
Storms may come, but we stay true,
Friends forever—me and you!##
  `.trim();

  const payload = {
    refer_voice: voiceId,
    refer_instrumental: instrumentalId,
    lyrics,
    model: "music-01",
  };

  const res = await fetch(url, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      Authorization: `Bearer ${API_KEY}`,
    },
    body: JSON.stringify(payload),
  });

  if (!res.ok) {
    const text = await res.text();
    throw new Error(`Generation failed ${res.status}: ${text}`);
  }

  const data = await res.json();
  const audioHex = data?.data?.audio;
  if (!audioHex) throw new Error("No audio hex in response");

  const audioBuffer = Buffer.from(audioHex, "hex");
  const outName = "generated_audio.mp3";
  await writeFile(outName, audioBuffer);
  console.log(`Generated audio saved as ${outName}`);
}

// Main function
async function main() {
  const uploaded = await uploadReferenceFile();
  if (!uploaded) return;

  // Extract IDs depending on purpose
  const voiceId = uploaded.voice_id;
  const instrumentalId = uploaded.instrumental_id;

  await generateAudio(voiceId, instrumentalId);
}

main();

Response

Upload successful: {'voice_id': 'vocal-2025082518145625-6XW9wCOF', 'instrumental_id': 'instrumental-2025082518145625-vCCEiiES', 'trace_id': '04fb6a8721abeee5b66edd452b4d0f33', 'base_resp': {'status_code': 0, 'status_msg': 'success'}}
Generated audio saved as generated_audio.mp3

Listen to the track we generated:

API Schemas

Generate a music sample

This endpoint uploads a reference music piece to the server, analyzes it, and returns identifiers for the voice and/or instrumental patterns to use later.

post

Authorizations

Body

filestring · binaryRequired

Audio file local path, supports WAV and MP3 formats. The audio duration must be longer than 10s and no more than 10 minutes.

purposestring · enumRequired

If purpose is song:

You need to upload a music file containing both acapella (vocals) and accompaniment.
The acapella must be in singing form; normal speech is not supported.
Outputs: voice_id and instrumental_id.

If purpose is voice:

You need to upload a file containing only acapella in singing form (normal speech audio is not supported).
Output: voice_id.

If purpose is instrumental:

You need to upload a file containing only accompaniment.
Output: instrumental_id.

Possible values:

Responses

default

application/json

default

{
  "voice_id": "vocal-2025011003141025-d5ZEMxmp",
  "instrumental_id": "instrumental-2025011003141125-Akz9eWnD",
  "base_resp": {
    "status_code": 1,
    "status_msg": "text"
  }
}

Generate music sample

This endpoint generates a new music piece based on the voice and/or instrumental pattern identifiers obtained from the first endpoint above. The generation can be completed in 50-60 seconds or take a bit more.

post

Authorizations

Body

all ofOptional

Responses

default

application/json

default

{
  "data": {
    "status": 1,
    "audio": "text"
  },
  "extra_info": {
    "audio_length": 1,
    "audio_size": 1,
    "audio_bitrate": 1,
    "audio_sample_rate": 1
  },
  "trace_id": "text",
  "base_resp": {
    "status_code": 1,
    "status_msg": "text"
  }
}

Previousminimax-music [legacy]NextStability AI

Last updated 1 month ago

Was this helpful?