The AI Music API for Songs, Jingles and Soundtracks
Send Revana an idea, a style or your own lyrics, and Suno's newest model writes and sings a full song or plays an instrumental. Every job returns two takes, so you can keep the better one. A job costs $0.08 with Suno V6 (prices as of November 2026), a job that fails costs nothing, and the request shape matches every other model on your key.
# One Idempotency-Key per job, made once: resend with the same $KEY after a timeout, a 429 or a 5xx
KEY=$(uuidgen)
curl https://api.revana.si/v1/generations \
-H "Authorization: Bearer $REVANA_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $KEY" \
-d '{
"model": "suno-v6",
"input": {
"prompt": "An upbeat song for a coffee shop opening on a sunny Saturday morning",
"style": "indie pop, warm female vocals, acoustic guitar, hand claps"
},
"max_cost_usd": 0.08
}'Songs, instrumentals and your own lyrics
Full songs with vocals
Describe the mood, the topic and the audience, and the model writes the words and sings them. Name a genre, such as upbeat pop punk with female vocals, to steer the sound.
Instrumentals for video and apps
Set instrumental to true and describe the music, such as lo-fi hip hop, soft piano and vinyl crackle: background tracks with no vocals to talk over.
Your lyrics, sung
Send your own words in lyrics with a style for the sound. Section tags such as [Verse] and [Chorus] on their own lines shape the song: a slogan becomes a jingle.
One public price per job
Each job costs $0.08 for both tracks, so a finished song works out at 4 cents. No credits per minute and no plan tiers: the bill is jobs times the listed price.
Four inputs and how they combine
Prompt describes the song
Use prompt for the idea in plain words: the mood, the subject, who it is for. It can run up to 3,000 characters; a longer prompt is refused before anything is charged, and most good prompts are a sentence or two.
Style sets the sound
Use style for genre, instruments and voice, such as indie folk with warm vocals. Keep a short list of styles that fit your product and reuse them, so every track sounds like it belongs.
Lyrics or instrumental
Send lyrics for words you want sung, or set instrumental to true for music without vocals. Two rules: every request needs a style or lyrics, or both, and lyrics and instrumental never go in the same request. A request that breaks a rule is refused and nothing is charged.
{
"model": "suno-v6",
"input": {
"prompt": "Calm background music for a product walkthrough video",
"style": "lo-fi hip hop, soft piano, vinyl crackle",
"instrumental": true
},
"max_cost_usd": 0.08
}{
"model": "suno-v6",
"input": {
"lyrics": "[Verse]\nMorning light and the first pour\n[Chorus]\nOpen doors, come on in",
"style": "folk pop, duet"
},
"max_cost_usd": 0.08
}What builders make with generated music
Soundtracks for generated video
Add a fresh instrumental under every clip your app makes. Revana returns the track as a file you mix into the video in your render step, so no two videos share the same five stock tracks.
Personal songs inside your app
Let users type a name and an occasion and get a song back, such as a birthday tune or a team anthem. At $0.08 a job, the feature is cheap to offer as a paid extra or a free delight.
Jingle and ad music variants
Test a slogan as a pop hook, a folk tune and a hip hop beat in one batch: ten jobs give you twenty takes for $0.80. Keep the version that tests best.
From prompt to two tracks in three calls
- Send the request. POST to
/v1/generationswith the music model and an input holding your prompt, style, lyrics or instrumental flag. Add anIdempotency-Keyso a resend after a timeout never makes a second job. - Quote it first, if you like. Send the same body to
/v1/generations/quoteand Revana returns the price without starting anything; quotes are free.max_cost_usdon the real request is your ceiling. - Download both takes. Poll the generation or receive a signed webhook when it finishes, then download the first take from
/contentand the second from/content/2. The response shows the exact charge incost_usd.
import os, time, uuid, requests
API = "https://api.revana.si/v1"
H = {"Authorization": f"Bearer {os.environ['REVANA_API_KEY']}"}
# made once: resend with the same key after a timeout and nothing is made or charged twice
key = str(uuid.uuid4())
job = requests.post(f"{API}/generations", headers={**H, "Idempotency-Key": key}, json={
"model": "suno-v6",
"input": {"prompt": "A short jingle for a bike shop", "style": "pop punk, bright guitars"},
"max_cost_usd": 0.08,
}).json()
while job["status"] not in ("succeeded", "failed"):
time.sleep(5)
job = requests.get(f"{API}/generations/{job['id']}", headers=H).json()
if job["status"] == "succeeded":
for n, path in ((1, "content"), (2, "content/2")): # two takes per job
song = requests.get(f"{API}/generations/{job['id']}/{path}", headers=H)
open(f"take-{n}.mp3", "wb").write(song.content)
print("charged", job["cost_usd"])Pay per song, never for a failed job
| ジョブ数 | トラック | 合計 |
|---|---|---|
| 1 | 2 | $0.08 |
| 10 | 20 | $0.80 |
| 100 | 200 | $8.00 |
| 1,000 | 2,000 | $80.00 |
Revana holds the price when you submit and releases it if the job fails, so a failed job shows as $0.00 and a batch of 1,000 songs never bills for the ones that did not come back. The music model runs on one route today, and its model page says so: if that route fails you pay nothing and can resend with a new Idempotency-Key.
Music, voice and video from one balance
Add a voiceover
Generate narration with ElevenLabs V3 on the same key, $0.21 per 1,000 characters, and lay it over your instrumental in your own mix step.
Video that brings its own sound
Some video models, such as Veo 3.1, make music and ambience with the picture. Use a music job when you want a full song or the same track across many clips.
One bill for the whole clip
Picture, voice and music are all paid from one prepaid balance: one invoice, one key to rotate, one integration.
Your first song in five minutes
- Create your key. Sign in with Google or an email link and create an API key in the dashboard. The key is free and works with every model, and price quotes are free too.
- Add credit from $10. Credit is prepaid, with no subscription and no monthly minimum, and it never expires. A $10 pack covers 125 music jobs at the November 2026 price; volume terms are on enterprise.
- Or ask your AI agent. Connect the Revana MCP server to Claude, ChatGPT, Cursor or VS Code and ask for a jingle in plain words. The agent quotes the job, makes both takes and hands back the files, on your prepaid credit.
FAQ
What is an AI music API?
An AI music API turns a text description, a style or a set of lyrics into a finished track your app can download. On Revana you call Suno's newest model with one key and the same request shape you use for video and images.
How much does a generated song cost?
One job costs $0.08 on Revana and returns two tracks, so each song works out at 4 cents (prices as of November 2026). You pay from prepaid credit with no subscription, and a failed job is not charged.
Why do I get two tracks?
Every music job returns two takes of the same request, so you can pick the stronger one or offer both to your users. Download the first from /content and the second from /content/2 once the job has succeeded.
Can I use my own lyrics?
Yes. Send your words in lyrics along with a style for the sound, and put section tags such as [Verse] and [Chorus] on their own lines to shape the song. The model writes the melody and sings your words.
Can it make music without vocals?
Yes. Set instrumental to true and describe the music in prompt and style, such as soft piano with vinyl crackle. Do not send lyrics in the same request: an instrumental request with lyrics is refused before anything is charged.
Can I use the songs commercially?
Commercial use depends on the music model maker's own terms, so read them before you publish or sell a track. The model page names its maker.
Am I charged if a song fails?
No. The price is held when you submit and released if the job fails, so a failed job shows as $0.00. Resend it with a new Idempotency-Key and you are charged once, only when the tracks are delivered.
Your first song in five minutes
Create your free Revana key, send a prompt and a style, and download two takes. Making music at volume? The Revana team can set up volume terms on the same key.