Let's be clear about one thing first: Suno's official "Custom Models" and Suno-API's "custom voices" and "voice cloning" are not the same thing. The former is a private feature inside your official Suno account, and our API cannot read across accounts. The latter is provided by Suno-API to make generated results use a specified voice. This article explains the two separately.
What the official Custom Models are
The following are all statements publicly written on the official Custom Models page (we checked on 2026-09-26):
| Official statement | Meaning |
|---|---|
| Fine-tune a model that fits your taste using your own uploaded content | It is trained, not picked from presets |
| You can create up to 3 custom models | There is a hard limit on the number |
| For your own use only | Not publicly released, and won't enter the public library |
| You must own the rights to the audio used for training, including your own Suno library | The material must be something you have the right to use |
| For safety and personalization, no one but you can access your custom models | Private resource, bound to the account |
The official page also lists five FAQs (what it is, what's required, how many you can have, who can use it, and whether V6 is supported), plus a Custom Models guide. For specific rules and current plan details, refer to the official page; we don't interpret them for you.
Three names that are easy to confuse
| Name | What it is | Belongs to |
|---|---|---|
| Custom Models | A dedicated model fine-tuned from your own audio; officially stated maximum of 3 | Your official account, only you can use it |
| Persona Voices | A voice feature in official plans, listed as one of the benefits in the official paid plan description | Your official account |
| Custom voices / voice cloning | Train a reusable singing voice from a recording, and specify it to sing when generating songs | Within the Suno-API account system |
Many people searching for "custom models" actually want the third effect—to have their own voice or style appear in the song. This need can be met with "custom voices" and does not require the official training entry point.
Why Suno-API cannot read custom models from your official account
Two reasons combine to make it mechanically impossible:
- Models are bound to accounts. Official Custom Models belong to the official account that created them, and Suno-API does not read personal models across accounts.
- It is a private resource within the account. Custom models are bound to the account that created them and do not migrate to other accounts with an API Key.
So if someone tells you "you can call your Suno custom models with our API," that statement does not hold up mechanically.
What Suno-API can do: custom voices (voice cloning)
Taking our platform as an example, the part that can be replaced is as follows:
| Step | Description |
|---|---|
| Creation | Upload or record a source voice, name it, and follow the wizard; there is a secondary verification in the middle to confirm the voice is your own |
| Billing | Voice verification, cloning, status query, deletion, and download are free; generating a song with a cloned voice costs 1.2 yuan per generation, which is twice the 0.6 yuan for a normal generation; with Max Mode enabled, it is 2.4 yuan per generation |
| Available combinations | Pure clone generation, cover plus clone, extend plus clone, inspiration plus clone |
| Cannot be stacked | Modes such as crop, speed change, reverse, fusion, sampling, replacement, add track, and stem separation will show as locked |
| Note | Voices may expire. It is recommended to verify availability before each use; see the voice cloning API for specific endpoints |
The complete step-by-step with screenshots is in the fourth article of the workbench tutorial; if you want to use the API directly, see voice cloning and specified voice generation API.
How to choose
| What you want | Which path to take |
|---|---|
| Sing my songs with my own voice | Voice cloning / custom voices, can use Suno-API directly |
| Fine-tune style and patterns into a model that is only mine, and use it only in the official account | Official Custom Models, only usable within the corresponding official account |
| Integrate generation into my own product and produce songs in bulk | Suno-API, starting from applying for a Key |
FAQ
Do custom models cost extra?
The official page does not publicly state pricing, and we don't guess. Plans and benefits are subject to the official page and your own account dashboard.
Do official custom models support V6?
The official FAQ does have this question, but the answer requires expanding the page to see. Refer to the official statement; we don't paraphrase it.
Can others use my cloned voice?
The voice is in your platform account and will only be specified when called with your account or a Key you issue; others cannot access it.
When I generate with Suno-API, can I specify a voice from my official account?
No. The two systems are separate: resources in the official account are only available within that official account, while Suno-API uses platform-side accounts.
Summary
In one sentence: Official custom models are a private training feature within an account, with a maximum of 3, and Suno-API does not read across accounts; Suno-API's "custom voices" solve the problem of "making a song sing with your voice," and this can be done right now. To hear the effect first, go to the workbench and generate a song with a cloned voice; to integrate into your own product, start by getting a Key.
¥0.6 per generation, 2 tracks, unlimited downloads
Runs on the Suno V6 engine. Download MP3 or WAV as often as you like. Signing up needs an email address, not a phone number.
