/MUSIC/suno

Audio

Dirilis 9 September 2026

Suno API

Pembuatan audio Suno: membuat lagu, lirik, dan efek suara, serta mengedit trek yang ada (extend, cover, stem, fades, mashup, remaster, MV, persona, dan lainnya) — satu model yang dipilih berdasarkan bidang `action`.

Teks ke musik
Referensi audio
Beberapa tindakan

Coba model Dapatkan Kunci API Dokumentasi

Mulai dari

$0.075

per generasi

53 parameter · 31 pilihan harga

Playground Suno

Masukan

Prompt

Custom mode: detailed lyrics / prompt (also the lyrics or sound description)

Audio URL

Audio file URL to operate on

Image URL

music-video: cover image URL to show inside the ring (default: the source track's cover art when available)

Voice Audio URL

voice: URL to the voice recording

Verification Audio URL

voice: URL to the verification-phrase recording

Audio URLs

Public audio URLs. inspo: 1–4 inspiration references; custom-model: 6–24 training tracks (MP3, WAV or M4A).

Masuk untuk menjalankan

Penggunaan akan dibebankan ke saldo Anda.

Keluaran

Keluaran akan muncul di sini.

Isi kolom, periksa biaya, lalu jalankan model. Hasil akan muncul di sini; Anda tidak memerlukan kunci API terpisah untuk mencoba di browser.

Harga API Suno

Opsi	Harga per generasi
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

Mulai cepat

Referensi API lengkap →

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      "makeInstrumental": false,
9      "maxMode": false,
10      "aspectRatio": "9:16",
11      "quality": "compact"
12    }
13  }'

Parameter

Nama	Jenis	Wajib	Default	Deskripsi
`action`	string	Tidak	music	Suno operationSalah satu dari: 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
`mv`	string	Tidak	—	Versi mesin. Aksi audio: v6 (default) \| v6-wild \| v6-mini \| custom. Versi lama v3.5 … v5.5 yang sudah dihentikan tetap diterima dan dijalankan di v6. lyrics: remi-v1 \| default. Tidak dipakai oleh stems/stems-all/wav/voice. variety, maxMode, audioFormat, duration, dan customModelId memerlukan mesin V6 (nilai apa pun kecuali custom).
`custom`	boolean	Tidak	—	false for simple mode, true for custom mode
`gptDescriptionPrompt`	string	Tidak	—	Simple mode: song / effect description (with optional lyrics)
`prompt`	string	Tidak	—	Custom mode: detailed lyrics / prompt (also the lyrics or sound description)
`tags`	string	Tidak	—	Custom mode: genre / style tags
`title`	string	Tidak	—	Title for the result
`makeInstrumental`	boolean	Tidak	false	Generate an instrumental-only track
`negativeTags`	string	Tidak	—	Styles to avoid (custom mode / sound)
`personaId`	string	Tidak	—	ID of a custom voice (persona) to sing the generated music
`customModel`	object	Tidak	—	Inline custom model definition (required when mv=custom)
`customModelId`	string	Tidak	—	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.
`variety`	string	Tidak	—	Style variation: off \| normal \| high \| extra \| max. V6 generative actions.Salah satu dari: off, normal, high, extra, max
`maxMode`	boolean	Tidak	false	Max mode: higher-quality V6 generation, billed at twice the regular price. Requires custom mode, except on inspo and replace-section.
`audioFormat`	string	Tidak	—	Output audio format: mp3 \| m4a \| wav. V6 generative actions plus sound, remaster, stems and stems-all.Salah satu dari: mp3, m4a, wav
`duration`	number	Tidak	—	music / extend / cover: target length in seconds (10–360), custom mode only. The actual length is decided by the model.
`audioUrl`	string	Tidak	—	Audio file URL to operate on
`continueAt`	number	Tidak	—	extend: time in seconds where the extension should begin (at least 1 for a sourceTaskId or audioUrl source)
`sourceTaskId`	string	Tidak	—	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.
`audioId`	string	Tidak	—	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.
`fullLyrics`	string	Tidak	—	replace-section: complete lyrics for the whole track after the edit
`author`	string	Tidak	—	music-video: artist / creator name on the cover (max 50)
`domainName`	string	Tidak	—	music-video: brand / site watermark at the bottom (max 50)
`aspectRatio`	string	Tidak	9:16	music-video: output aspect ratioSalah satu dari: 9:16, 16:9, 1:1, 3:4, 4:3
`backgroundColors`	string[]	Tidak	—	music-video: 1–4 hex colors for the blurred gradient backdrop (e.g. ["#1B2635", "#8A6A4F"])
`imageUrl`	string	Tidak	—	music-video: cover image URL to show inside the ring (default: the source track's cover art when available)
`quality`	string	Tidak	compact	music-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× compactSalah satu dari: compact, high, max
`startS`	number	Tidak	—	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).
`endS`	number	Tidak	—	End time (seconds) of the affected range (> startS). See startS for the actions that use it.
`bpm`	number	Tidak	—	sound: tempo in BPM
`key`	string	Tidak	—	sound: musical key (Major C–B; Minor Cm–Bm)
`type`	string	Tidak	—	sound: 'one-shot' or 'loop' (defaults to one-shot)Salah satu dari: one-shot, loop
`voiceAudioUrl`	string	Tidak	—	voice: URL to the voice recording
`verificationAudioUrl`	string	Tidak	—	voice: URL to the verification-phrase recording
`phraseId`	string	Tidak	—	voice: phrase ID from the verification-phrase endpoint
`name`	string	Tidak	—	voice / custom-model: name
`description`	string	Tidak	—	voice: description
`styles`	string	Tidak	—	voice: genre tags (e.g. 'funk edm')
`singerSkillLevel`	string	Tidak	—	voice: singer skill levelSalah satu dari: Beginner, Intermediate, Advanced, Professional
`audioUrls`	string[]	Tidak	—	Public audio URLs. inspo: 1–4 inspiration references; custom-model: 6–24 training tracks (MP3, WAV or M4A).
`styleWeight`	number	Tidak	—	Style weight (0.00–1.00)
`weirdnessConstraint`	number	Tidak	—	Creativity / weirdness weight (0.00–1.00)
`audioWeight`	number	Tidak	—	Audio weight (0.00–1.00)
`vocalGender`	string	Tidak	—	Vocal gender: Male or FemaleSalah satu dari: Male, Female
`autoLyrics`	boolean	Tidak	—	inspo: rewrite the provided lyrics creatively
`variationCategory`	string	Tidak	—	remaster: intensity (subtle / normal / high)Salah satu dari: subtle, normal, high
`stemType`	string	Tidak	—	stems: which stem to extract (e.g. lead_vocal, backing_vocals, drum_kit, bass, piano, electric_guitar). Defaults to lead_vocal.
`voxAudioId`	string	Tidak	—	Deprecated and ignored: a persona is now created straight from the track (voice with sourceTaskId), no vox extraction needed.
`durationS`	number	Tidak	—	fade-in / fade-out: fade duration in seconds
`speed`	number	Tidak	—	adjust-speed: speed multiplier (0.25–4)
`keepPitch`	boolean	Tidak	—	adjust-speed: keep the original pitch (defaults to true)
`sourceTaskIds`	string[]	Tidak	—	mashup: exactly 2 prior suno generation ids (taskIds) to remix together
`audioIds`	string[]	Tidak	—	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

Pertanyaan yang sering diajukan

Berapa biaya Suno?

Suno mulai dari $0.075 per generasi melalui API Stock API. Anda membayar sesuai penggunaan dari satu saldo prabayar — tidak ada langganan — dan harga akhir menyesuaikan parameter seperti resolusi atau durasi.

Kapan Suno dirilis?

Suno dirilis pada 9 September 2026. Model ini tersedia melalui API API Stock dengan kunci dan saldo prabayar yang sama seperti model lainnya.

Bagaimana cara mendapatkan kunci API untuk Suno?

Daftar di API Stock, isi saldo dengan metode pembayaran yang tersedia, lalu buat kunci API di dasbor — prosesnya hanya beberapa menit dan tanpa kontrak. Kunci yang sama berlaku untuk semua model di katalog, jadi Anda tidak perlu kunci terpisah untuk Suno.

Bagaimana cara memanggil API Suno?

Kirim permintaan POST ke https://api.api-stock.com/api/v1/generation/create dengan kunci API Anda dan ID model "suno". Panggilan ini mengembalikan ID tugas yang dapat Anda pantau, atau callback webhook saat hasil siap. Contoh yang siap dijalankan tersedia di bagian mulai cepat di atas.

Parameter input apa yang diterima Suno?

Suno menerima 53 parameter input. Jenis, nilai default, dan nilai yang diizinkan tercantum dalam tabel parameter di atas.

Apa yang terjadi jika permintaan Suno gagal?

API Stock otomatis mencoba kembali permintaan pada penyedia cadangan. Jika semua penyedia gagal, biaya dikembalikan ke saldo Anda.

Dapatkah saya menggunakan Suno dengan kunci API yang sama seperti model lain?

Ya. Setiap model di API Stock — video, gambar, musik, dan chat — menggunakan satu kunci API dan satu saldo prabayar, sehingga Anda dapat beralih ke Suno tanpa kredensial baru.