> ## Documentation Index > Fetch the complete documentation index at: https://docs.mountsea.ai/llms.txt > Use this file to discover all available pages before exploring further. # Custom Model > Create custom music models trained on your own audio Create a personalized music model trained on your own audio. The process requires three steps: **prepare** (create session) → **upload** (upload training audio, at least 6) → **create** (submit for training). ## Workflow ``` ① customModel/prepare │ Select account, create session │ Returns: { sessionId } │ ▼ ② customModel/upload ×N (at least 6) │ Upload audio files one by one (async) │ Returns: { taskId } │ Poll: GET /suno/v2/status?taskId=xxx │ Result contains clip info (including id) │ │ Can upload in parallel, each polled independently │ ▼ ③ customModel/create │ Submit clipIds + model name → Start training │ Returns: { taskId } (taskId = sessionId) │ Poll: GET /suno/v2/status?taskId=xxx │ Training takes ~2-3 minutes │ Result contains custom model details (including model ID) ▼ Done → Use model ID in /generate ``` *** ## Step 1: Prepare — Create Session Create a session and bind an account. All subsequent upload and create calls use the same account automatically. ### Request ``` POST /suno/v2/customModel/prepare ``` No request body required. ### Response ```json theme={null} { "sessionId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890" } ``` The `sessionId` is the unique identifier for the entire workflow. Keep it for subsequent steps. See [Prepare API Reference →](/api-reference/suno/customModelPrepare) *** ## Step 2: Upload — Upload Training Audio Upload audio files one at a time. Each call is async and returns a `taskId`. You need to poll until the task succeeds to get the `clipId` from the result. **Minimum 6 audio files** are required before you can proceed to the create step. Multiple uploads can run in parallel. ### Request ``` POST /suno/v2/customModel/upload ``` | Field | Type | Required | Description | | ----------- | ------------- | -------- | ------------------------------- | | `sessionId` | string (UUID) | Yes | Session ID from prepare step | | `audioUrl` | string (URL) | Yes | Publicly downloadable audio URL | ### Task Result On success, the `result` contains clip info including an `id` field — this is the `clipId` needed for the create step. See [Upload API Reference →](/api-reference/suno/customModelUpload) *** ## Step 3: Create — Submit for Training After collecting at least 6 clipIds from successful uploads, submit the training request. This costs **100 credits** and takes approximately **2-3 minutes**. ### Request ``` POST /suno/v2/customModel/create ``` | Field | Type | Required | Description | | ----------- | ------------- | -------- | ----------------------------------------- | | `sessionId` | string (UUID) | Yes | Session ID from prepare step | | `clipIds` | string\[] | Yes | Clip IDs from upload results (at least 6) | | `name` | string | Yes | Custom model name | The returned `taskId` equals the `sessionId`. You can poll using either one. On success, the `result` contains the custom model details. The model ID format is `chirp-custom:`. See [Create API Reference →](/api-reference/suno/customModelCreate) *** ## Using Your Custom Model Once training is complete, use the model ID directly in the [Generate](/api-reference/suno/generate) endpoint: ```json theme={null} { "task": "create", "model": "chirp-custom:3b285ad7-b09c-48fe-99e6-ec8a109f0650", "prompt": "[Verse]\nA catchy pop melody...", "tags": "Pop, Upbeat" } ``` The system automatically uses the same account that created the custom model for generation. *** ## Complete Example ```javascript Node.js theme={null} const API_BASE = 'https://api.mountsea.ai'; const headers = { 'Content-Type': 'application/json', 'Authorization': 'Bearer your-api-key' }; async function pollTask(taskId) { while (true) { const res = await fetch(`${API_BASE}/suno/v2/status?taskId=${taskId}`, { headers }); const task = await res.json(); if (task.status === 'success') return task.data; if (task.status === 'failed') throw new Error(task.failReason); await new Promise(r => setTimeout(r, 3000)); } } // Step 1: Prepare session const prepareRes = await fetch(`${API_BASE}/suno/v2/customModel/prepare`, { method: 'POST', headers }); const { sessionId } = await prepareRes.json(); console.log('Session ID:', sessionId); // Step 2: Upload audio files (at least 6, can run in parallel) const audioUrls = [ 'https://example.com/song1.mp3', 'https://example.com/song2.mp3', 'https://example.com/song3.mp3', 'https://example.com/song4.mp3', 'https://example.com/song5.mp3', 'https://example.com/song6.mp3', ]; const uploadPromises = audioUrls.map(async (audioUrl) => { const res = await fetch(`${API_BASE}/suno/v2/customModel/upload`, { method: 'POST', headers, body: JSON.stringify({ sessionId, audioUrl }) }); const { taskId } = await res.json(); const result = await pollTask(taskId); return result.id; // clipId }); const clipIds = await Promise.all(uploadPromises); console.log('Uploaded clips:', clipIds); // Step 3: Create custom model const createRes = await fetch(`${API_BASE}/suno/v2/customModel/create`, { method: 'POST', headers, body: JSON.stringify({ sessionId, clipIds, name: 'My Custom Model' }) }); const { taskId: createTaskId } = await createRes.json(); const model = await pollTask(createTaskId); console.log('Custom model created:', model); // Use model.id (e.g. "chirp-custom:xxx") in /generate ``` ```python Python theme={null} import requests import time from concurrent.futures import ThreadPoolExecutor API_BASE = 'https://api.mountsea.ai' headers = { 'Content-Type': 'application/json', 'Authorization': 'Bearer your-api-key' } def poll_task(task_id): while True: res = requests.get(f'{API_BASE}/suno/v2/status', params={'taskId': task_id}, headers=headers) task = res.json() if task['status'] == 'success': return task['data'] if task['status'] == 'failed': raise Exception(task.get('failReason', 'Unknown error')) time.sleep(3) def upload_audio(session_id, audio_url): res = requests.post(f'{API_BASE}/suno/v2/customModel/upload', headers=headers, json={ 'sessionId': session_id, 'audioUrl': audio_url }) result = poll_task(res.json()['taskId']) return result['id'] # Step 1: Prepare prepare_res = requests.post(f'{API_BASE}/suno/v2/customModel/prepare', headers=headers) session_id = prepare_res.json()['sessionId'] # Step 2: Upload (parallel) audio_urls = [f'https://example.com/song{i}.mp3' for i in range(1, 7)] with ThreadPoolExecutor(max_workers=6) as executor: clip_ids = list(executor.map(lambda url: upload_audio(session_id, url), audio_urls)) # Step 3: Create create_res = requests.post(f'{API_BASE}/suno/v2/customModel/create', headers=headers, json={ 'sessionId': session_id, 'clipIds': clip_ids, 'name': 'My Custom Model' }) model = poll_task(create_res.json()['taskId']) print(f"Custom model created: {model}") ``` ## Failure Recovery * **Upload fails**: Retry with the same `sessionId` — no need to re-prepare. * **Create fails** (e.g. parameter error): Retry with the same `sessionId` and corrected parameters. The system automatically resets the session state. * **Prepare** rarely fails since it only creates a session and binds an account. ## Important Notes The `create` step costs **100 credits**. Make sure all uploaded clips are correct before submitting. * **Same account guarantee**: prepare / upload / create automatically use the same Suno account — no manual specification needed. * **Credits**: The create step costs 100 credits. Upload steps also have minor credit costs based on task pricing configuration. * **ClipId validation**: All `clipIds` in the create request must come from uploads within the current session, otherwise a 400 error is returned. * **Parallel uploads**: Multiple upload requests can be sent concurrently without conflicts. * **Model limits**: Each custom account has a maximum number of models it can create, configured by the administrator.