/MUSIC/suno
Suno 在线试用
输入
Custom mode: detailed lyrics / prompt (also the lyrics or sound description)
Audio file URL to operate on
music-video: cover image URL to show inside the ring (default: the source track's cover art when available)
voice: URL to the voice recording
voice: URL to the verification-phrase recording
Public audio URLs. inspo: 1–4 inspiration references; custom-model: 6–24 training tracks (MP3, WAV or M4A).
登录后运行
运行费用将从您的余额中扣除。
输出
输出将显示在此处。
填写参数、确认费用并运行模型，结果将在此处显示。在浏览器中试用无需单独创建 API 密钥。
Suno API 价格
| 选项 | 每次生成的价格 |
|---|---|
| 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 |
快速开始
完整 API 参考 →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 }'
参数
| 名称 | 类型 | 必填 | 默认值 | 描述 |
|---|---|---|---|---|
action | string | 否 | music | Suno operation以下之一：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 | 否 | — | 引擎版本。音频操作：v6（默认）| v6-wild | v6-mini | custom。已停用的 v3.5 … v5.5 仍可传入，并在 v6 上运行。lyrics：remi-v1 | default。stems/stems-all/wav/voice 不使用此参数。variety、maxMode、audioFormat、duration 和 customModelId 需要 V6 引擎（custom 以外的任意值）。 |
custom | boolean | 否 | — | false for simple mode, true for custom mode |
gptDescriptionPrompt | string | 否 | — | Simple mode: song / effect description (with optional lyrics) |
prompt | string | 否 | — | Custom mode: detailed lyrics / prompt (also the lyrics or sound description) |
tags | string | 否 | — | Custom mode: genre / style tags |
title | string | 否 | — | Title for the result |
makeInstrumental | boolean | 否 | false | Generate an instrumental-only track |
negativeTags | string | 否 | — | Styles to avoid (custom mode / sound) |
personaId | string | 否 | — | ID of a custom voice (persona) to sing the generated music |
customModel | object | 否 | — | Inline custom model definition (required when mv=custom) |
customModelId | string | 否 | — | 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 | 否 | — | Style variation: off | normal | high | extra | max. V6 generative actions.以下之一：off, normal, high, extra, max |
maxMode | boolean | 否 | false | Max mode: higher-quality V6 generation, billed at twice the regular price. Requires custom mode, except on inspo and replace-section. |
audioFormat | string | 否 | — | Output audio format: mp3 | m4a | wav. V6 generative actions plus sound, remaster, stems and stems-all.以下之一：mp3, m4a, wav |
duration | number | 否 | — | music / extend / cover: target length in seconds (10–360), custom mode only. The actual length is decided by the model. |
audioUrl | string | 否 | — | Audio file URL to operate on |
continueAt | number | 否 | — | extend: time in seconds where the extension should begin (at least 1 for a sourceTaskId or audioUrl source) |
sourceTaskId | string | 否 | — | 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 | 否 | — | 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 | 否 | — | replace-section: complete lyrics for the whole track after the edit |
author | string | 否 | — | music-video: artist / creator name on the cover (max 50) |
domainName | string | 否 | — | music-video: brand / site watermark at the bottom (max 50) |
aspectRatio | string | 否 | 9:16 | music-video: output aspect ratio以下之一：9:16, 16:9, 1:1, 3:4, 4:3 |
backgroundColors | string[] | 否 | — | music-video: 1–4 hex colors for the blurred gradient backdrop (e.g. ["#1B2635", "#8A6A4F"]) |
imageUrl | string | 否 | — | music-video: cover image URL to show inside the ring (default: the source track's cover art when available) |
quality | string | 否 | 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× compact以下之一：compact, high, max |
startS | number | 否 | — | 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 | 否 | — | End time (seconds) of the affected range (> startS). See startS for the actions that use it. |
bpm | number | 否 | — | sound: tempo in BPM |
key | string | 否 | — | sound: musical key (Major C–B; Minor Cm–Bm) |
type | string | 否 | — | sound: 'one-shot' or 'loop' (defaults to one-shot)以下之一：one-shot, loop |
voiceAudioUrl | string | 否 | — | voice: URL to the voice recording |
verificationAudioUrl | string | 否 | — | voice: URL to the verification-phrase recording |
phraseId | string | 否 | — | voice: phrase ID from the verification-phrase endpoint |
name | string | 否 | — | voice / custom-model: name |
description | string | 否 | — | voice: description |
styles | string | 否 | — | voice: genre tags (e.g. 'funk edm') |
singerSkillLevel | string | 否 | — | voice: singer skill level以下之一：Beginner, Intermediate, Advanced, Professional |
audioUrls | string[] | 否 | — | Public audio URLs. inspo: 1–4 inspiration references; custom-model: 6–24 training tracks (MP3, WAV or M4A). |
styleWeight | number | 否 | — | Style weight (0.00–1.00) |
weirdnessConstraint | number | 否 | — | Creativity / weirdness weight (0.00–1.00) |
audioWeight | number | 否 | — | Audio weight (0.00–1.00) |
vocalGender | string | 否 | — | Vocal gender: Male or Female以下之一：Male, Female |
autoLyrics | boolean | 否 | — | inspo: rewrite the provided lyrics creatively |
variationCategory | string | 否 | — | remaster: intensity (subtle / normal / high)以下之一：subtle, normal, high |
stemType | string | 否 | — | stems: which stem to extract (e.g. lead_vocal, backing_vocals, drum_kit, bass, piano, electric_guitar). Defaults to lead_vocal. |
voxAudioId | string | 否 | — | Deprecated and ignored: a persona is now created straight from the track (voice with sourceTaskId), no vox extraction needed. |
durationS | number | 否 | — | fade-in / fade-out: fade duration in seconds |
speed | number | 否 | — | adjust-speed: speed multiplier (0.25–4) |
keepPitch | boolean | 否 | — | adjust-speed: keep the original pitch (defaults to true) |
sourceTaskIds | string[] | 否 | — | mashup: exactly 2 prior suno generation ids (taskIds) to remix together |
audioIds | string[] | 否 | — | 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 |
常见问题
Suno 的费用是多少？
Suno 通过 API Stock API 的起价为 $0.075 每次生成。您按使用量从单个预付余额中支付——无需订阅——最终价格会根据分辨率或时长等参数浮动。
Suno 是什么时候发布的？
Suno 于 2026年9月9日 发布。它可以通过 API Stock API 使用，与其他所有模型共用同一个 API 密钥和预付余额。
如何获取 Suno 的 API 密钥？
注册 API Stock 账号，使用可用的付款方式充值，然后在控制台创建 API 密钥即可，整个过程只需几分钟，无需签订合同。同一个密钥可调用目录中的所有模型，因此无需为 Suno 单独申请密钥。
如何调用 Suno API？
向 https://api.api-stock.com/api/v1/generation/create 发送 POST 请求，并附上您的 API 密钥和模型 ID "suno"。请求会返回一个任务 ID，您可以轮询该 ID；或者在结果准备就绪时通过 webhook 回调通知。上方的快速开始部分提供了一个可直接运行的示例。
Suno 接受哪些输入参数？
Suno 接受 53 个输入参数。参数表中列出了它们的类型、默认值和允许值。
如果 Suno 请求失败，会发生什么？
API Stock 会自动在备用提供商上重试请求。如果所有提供商都失败，费用会退还至您的余额。
我可以使用与其他模型相同的 API 密钥来调用 Suno 吗？
可以。API Stock 上的每个模型——视频、图像、音乐和聊天——共享一个 API 密钥和一个预付余额，因此您无需新的凭据即可切换到 Suno。