Generate Voice
Prepare the source and validation audio in the popup, then finish the self-built voice generation here.
The source clip will appear after the popup finishes.
The validation phrase will appear here after the popup starts the task.
The validation clip will appear here after the popup completes.
taskId: Not created yet
voiceId: Not ready yet
Transform your thoughts into songs instantly and unleash your creativity!
Transform your thoughts into songs instantly and unleash your creativity!
The task id of the original Suno generation task whose music links you want to recover.
Callback url notified when the task finishes. The recovery result is pushed to this address.
Transform your thoughts into songs instantly and unleash your creativity!
Task ID from the original music generation. Optional.
Maximum 100 characters
Audio start extension time point (in seconds). Must be greater than 0 and less than the total duration of the generated audio.
Apply a personaId to the generated music. Generate personaId at Generate Persona.
Transform your thoughts into songs instantly and unleash your creativity!
sounds task type supports up to 500 characters.
Whether to fetch lyric subtitles after generation is completed.
Whether to loop the generated sound.
BPM, valid range is 1-300. Empty means Auto.
Transform your thoughts into songs instantly and unleash your creativity!
Unique identifier of the music generation task.
Unique identifier of the specific audio track.
Retrieve synchronized lyrics with precise timestamps for music tracks. Both Task ID and Audio ID are required.
Query Voice Availability
Enter the generated taskId and query the voice availability result.
Run the query to see whether this voice is available.
Task ID from music generation (generate, extend, cover, upload-extend)
Audio ID from the completed music generation task
Name for the Persona
Detailed description of the Persona's musical characteristics
Start time (seconds)
End time (seconds)
Style description for the Persona (optional)
Create personalized music Personas for your generated music!
Original music task ID
Audio ID to replace
Prompt describing the replacement segment content
Music style tags
Music title
Start time (seconds)
End time (seconds)
Music styles to exclude (optional)
Complete lyrics after modification
Transform your thoughts into songs instantly and unleash your creativity!
Describe the theme, style, or subject of the desired lyrics. Maximum 200 characters.
Generate creative lyrics content based on a text prompt. Multiple variations of lyrics will be generated for each request.

Your refined music style will appear here. Enter a description and click 'Run' to start.
Task ID from a completed music generation task
Generate personalized cover images for your music!
Transform your thoughts into songs instantly and unleash your creativity!
Separate vocals and instruments from your audio tracks with AI!
Task ID from a completed vocal separation. This should be the taskId returned from the Vocal & Instrument Stem Separation endpoint.
Select the audio track to convert to MIDI format. Please fill in the Task ID field first.
Convert separated audio tracks into MIDI format with detailed note information for each instrument.
Upload up to 2 audio files to mashup music from multiple audio tracks.
Transform your thoughts into songs instantly and unleash your creativity!
Task ID from a completed "Generate Music" or "Extend Music" task
Audio ID from the completed music generation result
Artist or creator name to display as a signature on the video cover (max 50 characters)
Website or brand to display as a watermark at the bottom of the video (max 50 characters)
Create a video with visualizations based on your generated music track.
Transform your thoughts into songs instantly and unleash your creativity!
0/100
Optional Parameters
Transform your thoughts into songs instantly and unleash your creativity!
Transform your thoughts into songs instantly and unleash your creativity!
Convert your audio to WAV format for better compatibility!
README
Complete guide to using Suno API
Kie AI音乐API,经济高效的AI音乐集成解决方案
体验Kie AI音乐API带来的高质量音乐创作。享受流式音频输出、带时间戳的歌词和AI歌词助手。
Kie AI音乐API的主要功能
生成音乐
使用Kie AI音乐V6、V6 Mini和V6 Wild模型进行AI驱动的音乐创作,支持有无歌词的创作。每次请求可生成多个版本。提供自定义模式(必须填写标题,并至少提供风格、歌词或排除标签中的一项)和简易模式(根据你的创意自动写词,需至少提供风格、歌词或图片/视频/音频参考中的一项)。支持器乐和人声曲目的创作。非常适合开发者将强大的音乐生成能力集成至应用中。
生成歌词
Kie AI音乐API的歌词生成功能使用AI模型生成歌词,不生成音频曲目。它提供了一个简单且经济实惠的AI驱动歌词创作解决方案,响应速度快,并提供可定制选项。通过API集成,用户可以利用增强的Kie AI音乐元标签,处理复杂结构和情感深度,生成多种风格的歌词,包括摇滚、流行和说唱等。
扩展音乐
Kie AI音乐API的扩展音乐功能允许用户在保留原始风格和旋律的基础上,延长现有音轨。用户可以上传音频文件,并进行无缝扩展,确保输出质量高、过渡平滑。此功能支持自定义提示,指导扩展过程,用户可以指定音乐扩展的方式。
人声与伴奏音轨分离
Kie AI音乐API功能允许用户从完整歌曲中分离人声,或从人声轨道中提取伴奏部分。该API处理上传的音频文件,并返回清晰分离的音轨,开发者可以将人声分离功能集成到应用中,支持混音、卡拉OK制作、音乐制作及音频分析等用途。
生成音乐视频
Kie AI音乐API的生成音乐视频功能可以生成带有可视化效果的MP4视频,结合AI生成的音乐和视觉元素,创建完整的视听内容。该功能覆盖整个生产流程,包括音乐生成、图像生成、视频背景生成以及最终的音视频合成渲染。
上传与风格改编音频
Kie AI音乐API的上传与风格改编功能允许用户上传音频文件并将其转换为新的音乐风格,同时保留原始旋律。用户可以上传任何声音——从录音到示范——并将其转换为完整的歌曲。改编功能为歌曲注入全新风格,同时保持核心旋律不变。支持WAV等多种音频格式,能够无缝集成到音乐转换与创作应用中。
为什么选择Kie.ai进行AI音乐API的集成
一个接口支持 V6、V6 Mini 和 V6 Wild
在 POST /api/v1/jobs/createTask 里把 model 设为 V6、V6_MINI 或 V6_WILD。自定义模式下可用 duration 设定 10–360 秒的目标时长,歌词最多 5,000 字符,风格最多 1,000 字符。每次请求的积分见上方试用区。
简易模式支持图片、视频和音频参考
custom_mode 设为 false 时,可以用 image_urls、video_urls 和 audio_urls 引导歌曲(风格、歌词和所有参考合计不超过 10 个):图片最多 5 张(每张 10MB),视频 1 段、最长 241 秒,音频 6 秒到 30 分钟。
三阶段回调,文件保留 14 天
传入 callBackUrl,可在 text、first、complete 三个阶段收到通知,也可以用 taskId 轮询任务。每次请求生成多个版本,生成的文件保留 14 天。
如何在 Kie.ai 上使用 AI 音乐 API
注册并获取您的API密钥:
选择API端点和请求参数:
提交请求并监控进度:
常见问题解答
Kie AI音乐API提供哪些模型?
Kie AI音乐API提供三个模型:V6带来更强的音乐表现力、更自然的人声和更丰富的细节;V6 Mini轻量快速,兼顾质量与速度,创作更轻松;V6 Wild突破创作边界,带来更大胆、更有辨识度的音乐表达。V4 至 V5.5 等旧版本在 API 文档中已标为 Discontinued(已停用),请求时请使用 V6、V6_MINI 或 V6_WILD。
Kie AI音乐API包含哪些接口?
除 Generate Music 外,API 文档还列出了 Extend Music、Upload and Cover Audio、Upload and Extend Audio、Add Instrumental、Add Vocals、Replace Music Section、Generate Mashup Music、Generate Persona、Boost Music Style、Get Timestamped Lyrics、Generate Lyrics、Convert to WAV、Create Music Video、Vocal & Instrument Stem Separation、Generate MIDI from Audio、Generate Sounds、Generate Speech 以及自定义声音创建。
Kie AI音乐API的独特之处
Kie.ai 音乐 API 性价比高,包含 AI 驱动的歌词生成器、精确同步的时间戳歌词,以及适用于实时应用的快速流媒体输出等高级功能。
Kie.ai 音乐 API 的定价如何?
Generate Music、Extend Music、Upload and Cover Audio、Upload and Extend Audio、Add Instrumental 和 Add Vocals 每次请求均为 12 积分($0.06)。Generate Lyrics 和 Convert to WAV 为 0.4 积分($0.002),Create Music Video 为 2 积分($0.01),Vocal Separate 为 10 积分($0.05),Multi-Stem Separation 为 50 积分($0.25)。完整价格见 Kie.ai 价格页。价格可能会调整,请以本页顶部价格卡(选择模型类型)显示的价格为准。
Kie.ai 提供 AI 音乐 API 文档吗?
是的。Kie AI音乐API 文档列出了每个接口的参数和示例。Generate Music 走 POST https://api.kie.ai/api/v1/jobs/createTask,model 为 ai-music-api/generate,input.model 设为 V6、V6_MINI 或 V6_WILD。每次请求会生成多个版本并返回 taskId。传入 callBackUrl 可分三个阶段(text、first、complete)收到回调,也可以轮询 GET /api/v1/jobs/recordInfo?taskId=…;每首曲目都会返回 audio_url 和 stream_audio_url。生成的文件保留 14 天。
如何获取 Kie AI音乐API 的 API Key?
在 Kie.ai 注册后,到控制台的 API Keys 页面(kie.ai/api-key)创建密钥。每次请求都在请求头里带上 Authorization: Bearer YOUR_API_KEY;缺少密钥或密钥无效会返回 401 错误。
Kie.ai 提供 AI 音乐 API 的免费试用吗?
是的,Kie.ai 为新注册用户提供免费试用,允许他们在选择付费计划前测试音乐生成功能。