Suno API Alternative - Mureka V9 over REST, Pay per Song
Suno has no public API. Mureka V9 on Jantaris makes full songs from lyrics and a style prompt over REST, billed per song. Mureka vs Suno, stems, rights.
Suno does not have a public API. In July 2026 the company said it is exploring a developer API and will start with a curated group of partners, with no launch date. If you need songs with vocals generated from code today, Mureka V9 on Jantaris takes lyrics plus a style prompt and returns a finished track for $0.124 per song, charged per song from a prepaid balance with no subscription. The same balance covers audio tools for vocals, instrumentals and stems. Below: a factual Mureka vs Suno comparison, a Node.js pipeline that writes lyrics with a chat model and sings them with Mureka, and what the rights situation actually is.
Is there a Suno API?
As of October 2026:
- No official public API. No keys, no developer docs, no published API pricing.
- One is being explored. On July 1, 2026 Suno's chief product officer announced the company is exploring a developer API, starting with selected partners.
- "Suno API" search results are unofficial third-party services that drive accounts in Suno's consumer app. They are not a Suno product, so check Suno's terms before you build on one.
Suno itself runs as a web and mobile app with a free tier for non-commercial use and paid Pro and Premier plans that include commercial rights (plans and limits changed during 2026, so check suno.com). If you write music by hand in their app and like it, there is nothing to fix. An API makes sense when songs need to come out of your code, your workflow or your product.
Mureka V9 vs Suno
| Mureka V9 on Jantaris | Suno | |
|---|---|---|
| Access | REST API and Jantaris Studio in the browser | web and mobile app |
| Public API | yes (POST /v1/generate) | no, partner program being explored |
| Billing | per song from a prepaid balance | free tier plus credit-based subscriptions |
| Lyrics | required, up to 3,000 characters | your own, or generated by the app from a description |
| Style prompt | up to 1,024 characters, optional | yes |
| Instrumental | via Music Extractor | toggle in the app |
| Stems | Multistem Splitter | in the app, depends on plan |
Mureka (Kunlun Tech / Skywork AI) also runs its own API platform. On Jantaris you get the model on the same key and balance as image, video and chat models.
The practical difference: Mureka V9 does not invent lyrics. It sings exactly what you put in lyrics. If you are used to typing "a song about a cat who hates Mondays" and getting a full song, add a chat model step that writes the lyrics. The script below does exactly that.
Make a song in Jantaris Studio
- Open Studio, the Audio tab, and pick Mureka V9.
- In Prompt, describe the style: genre, tempo, vocal, instruments.
- In Lyrics, paste the text split with section tags.
- Check the cost under the form and click Generate.

Style prompts, [Verse] and [Chorus] tags and song length are covered in the Mureka V9 API guide. This post focuses on what people moving from Suno ask about: API access, automation and rights.
The pipeline: chat model writes, Mureka sings
Node.js 18+, no dependencies. One key for both steps:
const API = "https://jantaris.com/v1";
const headers = {
"Authorization": `Bearer ${process.env.JANTARIS_API_KEY}`,
"Content-Type": "application/json",
};
// 1. Lyrics from a chat model (OpenAI-compatible endpoint)
const chat = await fetch(`${API}/chat/completions`, {
method: "POST",
headers,
body: JSON.stringify({
model: "gemini-3.8-flash",
messages: [{
role: "user",
content: "Write short pop song lyrics about a cat who hates Mondays. " +
"Use [Verse], [Chorus], [Verse], [Chorus]. Repeat the chorus in full. No commentary.",
}],
}),
}).then((r) => r.json());
const lyrics = chat.choices[0].message.content;
// 2. The song from Mureka V9
let task = await fetch(`${API}/generate?wait=120`, {
method: "POST",
headers,
body: JSON.stringify({
model: "mureka-v9",
input: { lyrics, prompt: "upbeat indie pop, playful female vocal, ukulele, handclaps, 120 bpm" },
}),
}).then((r) => r.json());
// 3. Poll if the song was not ready within `wait`
while (!["succeeded", "failed"].includes(task.status)) {
await new Promise((r) => setTimeout(r, 5000));
task = await fetch(`${API}/tasks/${task.id}`, { headers }).then((r) => r.json());
}
if (task.status === "failed") throw new Error(task.error?.message ?? "generation failed");
console.log("song:", task.output[0].url, "cost:", task.cost);Notes for production:
- the
POSTresponse includesestimated_cost, so you know the price before the song is generated, - for batches, pass
webhook_urlinstead of polling; results arrive signed with HMAC-SHA256 (webhooks docs, and a full async pattern in AI pipelines with webhooks), - output URLs are temporary, so download the file right away,
- unknown fields such as
durationorinstrumentalreturn422, because Mureka V9 has no such parameters, - the chat endpoint is OpenAI-compatible, so the same key works in n8n, Make and the OpenAI SDK (no-code setup, OpenAI SDK with any model).

Audio tools you would look for after Suno
These work on any audio file at a public URL (audio_url):
| Tool | What it does | Price |
|---|---|---|
| Vocal Remover | isolates the vocal (acapella) | $0.50 per minute |
| Music Extractor | keeps the backing track, removes vocals | $0.50 per minute |
| Multistem Splitter | splits into vocals, drums and bass (price per minute, all three stems) | $1.50 per minute |
| Voice Cleaner | denoises speech recordings | $0.50 per minute |
| Music Video 1.0 | music video from an MP3 (10-300 s) and a few images | from $0.11 per second |

Tools bill per started minute of the source file, so trim silence first. Typical uses:
- instrumental for a voiceover reel: Mureka V9, then Music Extractor,
- remix or new mix: Multistem Splitter, then your DAW,
- vertical music video: Music Video 1.0 at 9:16.
These tools do not change who owns a recording. Only split and publish tracks you have the rights to.
Languages
Mureka V9's published language list covers English, Chinese, Japanese, Korean, Spanish, Portuguese, French, German, Italian and Russian. Other languages get sung too, but expect an accent. For English lyrics this is a non-issue.
Rights to Mureka V9 songs
I will not promise a license I do not have in writing. Here is where things stand:
- the output is yours within the law and the terms of Mureka as the model vendor,
- prompts and outputs are not used by Jantaris to train models,
- before you release on streaming services, check your distributor's rules for AI-generated music, since they differ,
- the lyrics you submit must be yours or licensed.
What it costs
Mureka V9 is $0.124 per song regardless of length. A sample month for a content creator:
| Item | Quantity | Cost |
|---|---|---|
| Mureka V9 songs | 20 songs | 20 × $0.124 per song |
| Instrumentals | 5 tracks of 3 minutes | 15 × $0.50 per minute |
| Lyrics from a chat model | 20 requests | cents, billed per token |
Minimum top-up is $10, the balance never expires and failed generations cost nothing. Rates are on the pricing page. To combine a song with images and video, see the AI product ad workflow.
FAQ
Does Suno have an official API?
No. In July 2026 Suno said it is exploring a developer API starting with selected partners, but there is no public access, documentation or pricing yet. Services sold as "Suno API" are unofficial wrappers.
Mureka vs Suno: which should I use?
If you make music by hand and want the app to write lyrics for you, Suno is convenient. If songs need to be generated by your code or workflow, often in many variations, Mureka V9 over an API gives you per-song billing and one balance shared with other models.
Is there a free Suno API alternative?
Jantaris has no free plan or signup credits; the minimum top-up is $10 and you only pay for successful songs. Vendor apps offer limited free tiers, usually for non-commercial use.
Can Mureka V9 make instrumentals?
Not directly: lyrics are required and there is no instrumental switch. Generate the song, then run it through Music Extractor to keep only the backing track.
Can I release Mureka V9 songs on Spotify?
The output is yours within the law and Mureka's terms. Check your distributor's AI music policy before uploading and make sure you own the lyrics.
How much does an AI song cost over the API?
$0.124 per song with Mureka V9, whatever the length. There is no monthly fee: you top up a balance from $10 and each finished song is charged from it.












