/MUSIC/suno
Audio

Suno API

Use one API Stock key for Suno music generation and editing. Choose the action for the job: composing music, extending a track and separating stems are separate requests with separate prices. This page documents access through API Stock, not a key issued by Suno.

  • Text to music
  • Audio reference
  • Multiple actions

Starting at

$0.075

per generation

53 parameters · 31 price options

Suno API pricing

OptionPrice per generation
music$0.075
bpm$0.002
vox$0.002
wav$0.002
concat$0.002
boost-style$0.002
music-video$0.002
timestamped-lyrics$0.002
upload$0.006
crop$0.012
lyrics$0.012
fade-in$0.012
fade-out$0.012
remove-section$0.012
sound$0.015
voice$0.024
adjust-speed$0.036
midi$0.075
cover$0.075
extend$0.075
mashup$0.075
sample$0.075
add-stem$0.075
remaster$0.075
add-vocals$0.075
music-cover$0.075
replace-section$0.075
add-instrumental$0.075
inspo$0.102
stems$0.15
stems-all$0.36
1curl -X POST https://api.api-stock.com/api/v1/generation/create \
2 -H "Authorization: Bearer $API_STOCK_KEY" \
3 -H "Content-Type: application/json" \
4 -d '{
5 "model": "suno",
6 "input": {
7 "action": "music",
8 "custom": false,
9 "gptDescriptionPrompt": "Warm acoustic folk with brushed drums and gentle piano for a quiet morning scene",
10 "makeInstrumental": true
11 }
12 }'

Choose this model for

Create an instrumental bed for a scene
Use action music, custom false and makeInstrumental true. Describe the mood, instruments and intended scene in gptDescriptionPrompt, then listen for space around a planned voiceover.
Develop your own lyrics or an existing track
For your own lyrics, select custom mode and put the words in prompt. For later editing, keep the chosen track's audioId from the completed result; each extension or stems action is another request.

Alternatives

Choose the Suno action for the job
Use sound for a short effect or loop, lyrics for text without an audio file, and stems to separate an existing track. A full music request is unnecessary for each of these jobs.
Text models
Use a text model when you only need a narration script or a scene outline. A music-generation result does not replace a spoken voiceover workflow.

What does a Suno API workflow cost?

Prices are per action request, not per minute. USD examples below use the current catalog with Max mode off. Max mode doubles the action price where supported. Editing and extraction actions add to the cost of the original generation.

Request configurationCost (USD)
One music request, Max mode off$0.075
One sound-effect request$0.015
Music followed by one stems request$0.225
Ten separate music requests, Max mode off$0.75

Get your first result

  1. Create an account and API key. Keep the key on your server, outside browser code.
  2. Top up your balance to cover the request price.
  3. Use the playground or the API quick start above. For your first instrumental, set action to music, custom to false and write the idea in gptDescriptionPrompt. For your own lyrics, use custom mode and its prompt field instead. The create response is a task ID, not an audio file; wait for completion and keep output.tracks[].audioId for later editing.

Check progress with the returned taskId. Creating a new task charges for another request.

1curl https://api.api-stock.com/api/v1/task/status/YOUR_TASK_ID \
2 -H "Authorization: Bearer $API_STOCK_KEY"

The task response reference covers results, errors and webhooks.

Recorded result

First 30 seconds of the first returned file, generated 15 October 2026 with the request on this page. One music request, Custom and Max mode off; no replacement takes. This is a delivery example, not a quality benchmark. Inputs and method

Limits and test notes

  • The recorded single music request returned two audio files. The player is only the first 30 seconds of the first file; it does not demonstrate the full arrangement or every Suno action.
  • The task was first observed finished about 332 seconds after creation. That includes queueing, processing and polling; one run does not establish typical latency.
  • A finished task confirms delivery. Listen to the complete track against your brief before using it, and budget another request if the arrangement is unsuitable. This run does not establish a musical approval rate.

Parameters

NameTypeRequiredDefaultDescription
actionstringNomusicSuno operationOne of: music, extend, cover, add-instrumental, add-vocals, sound, stems, stems-all, wav, lyrics, voice, timestamped-lyrics, boost-style, music-cover, replace-section, music-video, inspo, upload, remaster, add-stem, vox, remove-section, crop, fade-in, fade-out, adjust-speed, concat, mashup, sample, midi, bpm, custom-model
mvstringNo—Engine version. Audio actions: v6 (default) | v6-wild | v6-mini | custom. The retired versions v3.5 … v5.5 are still accepted and run on v6. lyrics: remi-v1 | default. Not used by stems/stems-all/wav/voice. variety, maxMode, audioFormat, duration and customModelId need a V6 engine (any value except custom).
custombooleanNo—false for simple mode, true for custom mode
gptDescriptionPromptstringNo—Simple mode: song / effect description (with optional lyrics)
promptstringNo—Custom mode: detailed lyrics / prompt (also the lyrics or sound description)
tagsstringNo—Custom mode: genre / style tags
titlestringNo—Title for the result
makeInstrumentalbooleanNofalseGenerate an instrumental-only track
negativeTagsstringNo—Styles to avoid (custom mode / sound)
personaIdstringNo—ID of a custom voice (persona) to sing the generated music
customModelobjectNo—Inline custom model definition (required when mv=custom)
customModelIdstringNo—Id of a reusable custom model created by the `custom-model` action (its `output.customModelId`). Generates in that model's style; cannot be combined with mv or personaId.
varietystringNo—Style variation: off | normal | high | extra | max. V6 generative actions.One of: off, normal, high, extra, max
maxModebooleanNofalseMax mode: higher-quality V6 generation, billed at twice the regular price. Requires custom mode, except on inspo and replace-section.
audioFormatstringNo—Output audio format: mp3 | m4a | wav. V6 generative actions plus sound, remaster, stems and stems-all.One of: mp3, m4a, wav
durationnumberNo—music / extend / cover: target length in seconds (10–360), custom mode only. The actual length is decided by the model.
audioUrlstringNo—Audio file URL to operate on
continueAtnumberNo—extend: time in seconds where the extension should begin (at least 1 for a sourceTaskId or audioUrl source)
sourceTaskIdstringNo—Reference to one of your prior Suno generations (its taskId), used by stateful actions such as extend, music-cover, replace-section, timestamped-lyrics, music-video, voice and wav.
audioIdstringNo—The track to operate on, identified by its id (as returned in a prior generation's `output.tracks[].audioId`). A generation usually produces 2 tracks; omit to use the first.
fullLyricsstringNo—replace-section: complete lyrics for the whole track after the edit
authorstringNo—music-video: artist / creator name on the cover (max 50)
domainNamestringNo—music-video: brand / site watermark at the bottom (max 50)
aspectRatiostringNo9:16music-video: output aspect ratioOne of: 9:16, 16:9, 1:1, 3:4, 4:3
backgroundColorsstring[]No—music-video: 1–4 hex colors for the blurred gradient backdrop (e.g. ["#1B2635", "#8A6A4F"])
imageUrlstringNo—music-video: cover image URL to show inside the ring (default: the source track's cover art when available)
qualitystringNocompactmusic-video: output quality. `compact` — small share-friendly file (~5MB / 3 min); `high` — sharper 720p-class output at roughly double the size; `max` — 1080p-class, ~4× compactOne of: compact, high, max
startSnumberNo—Start time (seconds) of the affected range. Used by remove-section / crop / sample (the range), replace-section (the infill range) and vox / voice-from-track (the vocal window).
endSnumberNo—End time (seconds) of the affected range (> startS). See startS for the actions that use it.
bpmnumberNo—sound: tempo in BPM
keystringNo—sound: musical key (Major C–B; Minor Cm–Bm)
typestringNo—sound: 'one-shot' or 'loop' (defaults to one-shot)One of: one-shot, loop
voiceAudioUrlstringNo—voice: URL to the voice recording (MP3 / WAV, at least 10 seconds)
verificationAudioUrlstringNo—voice: URL to the verification-phrase recording
phraseIdstringNo—voice: phrase ID from the verification-phrase endpoint
namestringNo—voice / custom-model: name
descriptionstringNo—voice: description
stylesstringNo—voice: genre tags (e.g. 'funk edm')
singerSkillLevelstringNo—voice: singer skill levelOne of: Beginner, Intermediate, Advanced, Professional
audioUrlsstring[]No—Public audio URLs. inspo: 1–4 inspiration references; custom-model: 6–24 training tracks (MP3, WAV or M4A).
styleWeightnumberNo—Style weight (0.00–1.00)
weirdnessConstraintnumberNo—Creativity / weirdness weight (0.00–1.00)
audioWeightnumberNo—Audio weight (0.00–1.00)
vocalGenderstringNo—Vocal gender: Male or FemaleOne of: Male, Female
autoLyricsbooleanNo—inspo: rewrite the provided lyrics creatively
variationCategorystringNo—remaster: intensity (subtle / normal / high)One of: subtle, normal, high
stemTypestringNo—stems: which stem to extract (e.g. lead_vocal, backing_vocals, drum_kit, bass, piano, electric_guitar). Defaults to lead_vocal.
voxAudioIdstringNo—Deprecated and ignored: a persona is now created straight from the track (voice with sourceTaskId), no vox extraction needed.
durationSnumberNo—fade-in / fade-out: fade duration in seconds
speednumberNo—adjust-speed: speed multiplier (0.25–4)
keepPitchbooleanNo—adjust-speed: keep the original pitch (defaults to true)
sourceTaskIdsstring[]No—mashup: exactly 2 prior suno generation ids (taskIds) to remix together
audioIdsstring[]No—mashup: parallel array to sourceTaskIds selecting the track in each source by its audioId (as returned in output.tracks[].audioId); omit an entry to use that source's first track

Frequently asked questions

Is this a Suno-issued API key?

No. The key is issued by API Stock and authenticates requests to the API Stock endpoint. A Suno website login or subscription is not the credential used in the examples on this page.

Is there a free Suno API trial on this page?

The API and playground use your prepaid API Stock balance. Creating an account or a key does not include a paid generation. Check the selected action price before topping up or starting a workflow.

Why did my Suno request return a task ID instead of audio?

Generation is asynchronous. Poll GET /api/v1/task/status/{taskId} for that task until it finishes, then read files and output. Keep the selected output.tracks[].audioId if you plan to extend or edit a particular track.

How much does Suno cost?

Suno starts at $0.075 per generation on API Stock. The final charge depends on the selected settings.

When was Suno released?

Suno was released on September 9, 2026 and is available through API Stock.

How do I get an API key for Suno?

Create an account and API key on API Stock, then fund your balance. The same key works with Suno and other catalog models.

How do I call the Suno API?

POST to https://api.api-stock.com/api/v1/generation/create with your API key and model "suno". Use the returned task id for polling or receive a webhook.

What input parameters does Suno accept?

Suno accepts 53 input parameters. See their types, defaults and allowed values above.

What happens if a Suno request fails?

API Stock automatically retries the request on a reserve provider. If every provider fails, the charge is refunded to your balance.

Can I use Suno with the same API key as other models?

Yes. Use your API Stock API key and balance for Suno and other catalog models.

Read next