API Reference

Suno Stem Layering

Suno Stem Layering: suno/add-stem.

POST https://api.tu-zi.com/suno/v2/add-stem

Preview guide

Paste into an AI assistant to help with integration. Documentation and examples only; no real credentials.

# Suno Stem Layering

Suno Stem Layering: suno/add-stem.

## Endpoint and authentication

`POST https://api.tu-zi.com/suno/v2/add-stem`

Transport: json

Use an inference API key. Examples contain placeholders; read credentials from environment variables.

```http
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
```

## Body parameters

| Field | Type | Required | Description / constraints |
| --- | --- | --- | --- |
| mv | string | No | All three versions are priced the same; pick by the style you want. Form initial value (not an upstream default): "chirp-v6" Values: "chirp-v6", "chirp-v6-wild", "chirp-v6-mini" Example: chirp-v6 |
| custom | boolean | Yes | Off: describe the song in one line. On: supply your own full lyrics. Form initial value (not an upstream default): false Example: false |
| gpt_description_prompt | string | No | One line describing the song you want. Required when custom mode is off. Up to 3000 characters. |
| prompt | string | No | Full lyrics, up to 5000 characters. Use markers like [Verse] and [Chorus] to shape the structure. |
| title | string | No | Track title, up to 80 characters. |
| tags | string | No | The style you want, e.g. 'lo-fi piano, mellow, rain'. Up to 1000 characters. |
| negative_tags | string | No | Styles to steer away from. |
| style_weight | number | No | 0 to 1. Higher sticks closer to your style tags; lower leaves more room to improvise. |
| weirdness_constraint | number | No | 0 to 1. Higher yields more unexpected results; lower stays conventional. |
| audio_weight | number | No | 0 to 1. How strongly the reference audio shapes the result. |
| variety | string | No | How far the result may drift from the style you specified. Values: "off", "normal", "high", "extra", "max" |
| max_mode | boolean | No | Spend more compute to keep the whole song coherent. Custom mode only; doubles the price. Form initial value (not an upstream default): false |
| model_id | string | No | Generate with a model you trained. Use the model_id from a create-model result. Cannot be combined with persona_id. |
| audio_format | string | No | Format of the finished audio. Defaults to mp3. Values: "mp3", "m4a", "wav" |
| music_id | string | Yes | The track to work on. Use the music_id from an earlier result. Example: MUSIC_ID |

## Minimal request example

```json
{
  "mv": "chirp-v6",
  "custom": false,
  "music_id": "MUSIC_ID"
}
```

## Before running

Replace https://api.tu-zi.com with this site origin (do not append /v1 twice), and YOUR_MODEL with the exact marketplace model ID. Install requests for Python; use Node.js 20+ and save JavaScript as .mjs. WebSocket samples list their own dependencies.

Create an inference key on the site and set API_KEY in the environment; replace YOUR_API_KEY in cURL. Prepare local input.png/input.wav files for upload examples.

Start with a minimal request, then read the result using the response fields below. For async APIs, a returned task ID requires polling; acceptance does not mean generation has finished.

## Code examples

### curl

```bash
curl --request POST 'https://api.tu-zi.com/suno/v2/add-stem' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
  "mv": "chirp-v6",
  "custom": false,
  "music_id": "MUSIC_ID"
}'
```

### python

```python
import json
import os
import requests

url = "https://api.tu-zi.com/suno/v2/add-stem"
headers = json.loads("{\"Authorization\":\"Bearer YOUR_API_KEY\",\"Content-Type\":\"application/json\"}")
headers["Authorization"] = "Bearer " + os.environ["API_KEY"]
payload = json.loads("{\"mv\":\"chirp-v6\",\"custom\":false,\"music_id\":\"MUSIC_ID\"}")
response = requests.request("POST", url, headers=headers, json=payload, timeout=120)
response.raise_for_status()
result = response.json()
if isinstance(result, dict) and (result.get("success") is False or result.get("error")):
    raise RuntimeError(json.dumps(result, ensure_ascii=False))
print(result)  # Also inspect protocol-specific status/code fields.
```

### javascript

```javascript
// Node.js 20+
const url = "https://api.tu-zi.com/suno/v2/add-stem";
const headers = {
  "Authorization": "Bearer YOUR_API_KEY",
  "Content-Type": "application/json"
};
headers.Authorization = 'Bearer ' + process.env.API_KEY;
const response = await fetch(url, { method: "POST", headers, body: JSON.stringify({
  "mv": "chirp-v6",
  "custom": false,
  "music_id": "MUSIC_ID"
}) });
if (!response.ok) throw new Error(await response.text());
const result = await response.json();
if (result?.success === false || result?.error) throw new Error(JSON.stringify(result));
console.log(result); // Also inspect protocol-specific status/code fields.
```

## Response fields

| Field | Type | Description / constraints |
| --- | --- | --- |
| code | string | Submission result code. |
| data.task_id | string | Public gateway task ID. |

Illustrative response; some endpoints show essential fields only. Optional fields may be absent.

```json
{
  "code": "success",
  "data": {
    "task_id": "task_example"
  }
}
```

## Asynchronous workflow

Save the public task ID and GET /suno/v2/fetch/{task_id} with the same key. Handle gateway states; SUCCESS and FAILURE are terminal. Read music, lyrics, download links or resource IDs according to the action.

## Errors and retries

Check HTTP status and protocol-specific errors; do not mix error formats across protocols. For 401/403 check credentials and permissions, for 429 back off, and for 5xx check gateway/upstream status. Error bodies may contain error/message/code depending on the protocol.

Use bounded exponential backoff for reads. Do not blindly retry task creation, generation, or key mutations, to avoid duplicate billing or execution.

## Constraints

Model suno/add-stem is selected by the action route, so the body does not need model. Resource IDs must belong to this account and be created through the gateway; do not use upstream internal IDs.

## Documentation source

Definition version: 1

Reviewed: 2026-11-02

Source: https://api.tu-zi.com/en/docs/api/reference-relay-suno-v2-add-stem

Related protocol guide: https://api.tu-zi.com/docs/api/suno

This export contains documentation and examples only, without real credentials, account data or user requests.

Updated 2026-11-02 · Reviewed 2026-11-02

Endpoint and authentication

POST https://api.tu-zi.com/suno/v2/add-stem

Transport: json

Use an inference API key. Examples contain placeholders; read credentials from environment variables.

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Minimal request example

{
  "mv": "chirp-v6",
  "custom": false,
  "music_id": "MUSIC_ID"
}

Before running

Replace https://api.tu-zi.com with this site origin (do not append /v1 twice), and YOUR_MODEL with the exact marketplace model ID. Install requests for Python; use Node.js 20+ and save JavaScript as .mjs. WebSocket samples list their own dependencies.

Create an inference key on the site and set API_KEY in the environment; replace YOUR_API_KEY in cURL. Prepare local input.png/input.wav files for upload examples.

Start with a minimal request, then read the result using the response fields below. For async APIs, a returned task ID requires polling; acceptance does not mean generation has finished.

Constraints

Model suno/add-stem is selected by the action route, so the body does not need model. Resource IDs must belong to this account and be created through the gateway; do not use upstream internal IDs.

Body parameters

Field	Type	Required	Description / constraints
mv	string	No	All three versions are priced the same; pick by the style you want. Form initial value (not an upstream default): "chirp-v6" Values: "chirp-v6", "chirp-v6-wild", "chirp-v6-mini" Example: chirp-v6
custom	boolean	Yes	Off: describe the song in one line. On: supply your own full lyrics. Form initial value (not an upstream default): false Example: false
gpt_description_prompt	string	No	One line describing the song you want. Required when custom mode is off. Up to 3000 characters.
prompt	string	No	Full lyrics, up to 5000 characters. Use markers like [Verse] and [Chorus] to shape the structure.
title	string	No	Track title, up to 80 characters.
tags	string	No	The style you want, e.g. 'lo-fi piano, mellow, rain'. Up to 1000 characters.
negative_tags	string	No	Styles to steer away from.
style_weight	number	No	0 to 1. Higher sticks closer to your style tags; lower leaves more room to improvise.
weirdness_constraint	number	No	0 to 1. Higher yields more unexpected results; lower stays conventional.
audio_weight	number	No	0 to 1. How strongly the reference audio shapes the result.
variety	string	No	How far the result may drift from the style you specified. Values: "off", "normal", "high", "extra", "max"
max_mode	boolean	No	Spend more compute to keep the whole song coherent. Custom mode only; doubles the price. Form initial value (not an upstream default): false
model_id	string	No	Generate with a model you trained. Use the model_id from a create-model result. Cannot be combined with persona_id.
audio_format	string	No	Format of the finished audio. Defaults to mp3. Values: "mp3", "m4a", "wav"
music_id	string	Yes	The track to work on. Use the music_id from an earlier result. Example: MUSIC_ID

Response fields

Field	Type	Description / constraints
code	string	Submission result code.
data.task_id	string	Public gateway task ID.

Illustrative response; some endpoints show essential fields only. Optional fields may be absent.

{
  "code": "success",
  "data": {
    "task_id": "task_example"
  }
}

Asynchronous workflow

Save the public task ID and GET /suno/v2/fetch/{task_id} with the same key. Handle gateway states; SUCCESS and FAILURE are terminal. Read music, lyrics, download links or resource IDs according to the action.

Errors and retries

Check HTTP status and protocol-specific errors; do not mix error formats across protocols. For 401/403 check credentials and permissions, for 429 back off, and for 5xx check gateway/upstream status. Error bodies may contain error/message/code depending on the protocol.

Use bounded exponential backoff for reads. Do not blindly retry task creation, generation, or key mutations, to avoid duplicate billing or execution.

Document information and sources

Documentation source

Definition version: 1

Reviewed: 2026-11-02

Source: https://api.tu-zi.com/en/docs/api/reference-relay-suno-v2-add-stem

Related protocol guide: https://api.tu-zi.com/docs/api/suno

This export contains documentation and examples only, without real credentials, account data or user requests.

Request examples

curl --request POST 'https://api.tu-zi.com/suno/v2/add-stem' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
  "mv": "chirp-v6",
  "custom": false,
  "music_id": "MUSIC_ID"
}'

import json
import os
import requests

url = "https://api.tu-zi.com/suno/v2/add-stem"
headers = json.loads("{\"Authorization\":\"Bearer YOUR_API_KEY\",\"Content-Type\":\"application/json\"}")
headers["Authorization"] = "Bearer " + os.environ["API_KEY"]
payload = json.loads("{\"mv\":\"chirp-v6\",\"custom\":false,\"music_id\":\"MUSIC_ID\"}")
response = requests.request("POST", url, headers=headers, json=payload, timeout=120)
response.raise_for_status()
result = response.json()
if isinstance(result, dict) and (result.get("success") is False or result.get("error")):
    raise RuntimeError(json.dumps(result, ensure_ascii=False))
print(result)  # Also inspect protocol-specific status/code fields.

// Node.js 20+
const url = "https://api.tu-zi.com/suno/v2/add-stem";
const headers = {
  "Authorization": "Bearer YOUR_API_KEY",
  "Content-Type": "application/json"
};
headers.Authorization = 'Bearer ' + process.env.API_KEY;
const response = await fetch(url, { method: "POST", headers, body: JSON.stringify({
  "mv": "chirp-v6",
  "custom": false,
  "music_id": "MUSIC_ID"
}) });
if (!response.ok) throw new Error(await response.text());
const result = await response.json();
if (result?.success === false || result?.error) throw new Error(JSON.stringify(result));
console.log(result); // Also inspect protocol-specific status/code fields.