创作音乐
使用 Lyria 3 Pro 生成音乐
taskId — 使用获取任务状态来轮询生成的音频。提示
- 音效提示:描述音乐风格、氛围、乐器和节奏(例如
"emotional pop with gentle piano, warm synths, and a catchy beat") - 歌词:使用段落标签如
[Verse]、[Chorus]、[Bridge]来获得结构化输出 - 图片引导:提供
imageUrl让模型从图片中推断氛围和风格 - 纯器乐:设置
makeInstrumental: true生成无人声曲目 - 可重复性:使用
seed进行确定性生成 — 相同的 seed + 相同的参数 = 相同的输出
授权
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
请求体
Action type to perform
create_music "create_music"
Sound/style prompt describing the desired music style
"driving energetic beat, rapid rhythm, high BPM"
Lyrics content with section tags like [Verse], [Chorus], etc. For create_music: either soundPrompt or lyrics should be provided. Set makeInstrumental=true to ignore lyrics.
"[Verse 1]\nI've been running in circles...\n\n[Chorus]\nI keep coming back to you..."
Song title (max 80 characters)
80"Back to You"
Music generation model (currently only Lyria 3 Pro)
Lyria 3 Pro "Lyria 3 Pro"
Random seed for reproducible generation
877369
Generate instrumental only (ignores lyrics). Default: false
false
Image URL for image-guided generation (will be uploaded automatically)
"https://example.com/cover.jpg"
响应
任务创建成功
任务 ID,用于后续查询结果