Create music from text prompts or composition plans
prompt — quick and easycompositionPlan with section-level control over styles, duration, and lyricstaskId — use Get Task Status to poll for the generated audio.prompt to describe the desired music. Optionally set forceInstrumental: true to generate without vocals.
compositionPlan with positive_global_styles, negative_global_styles, and a sections array. Each section can have its own section_name, positive_local_styles, negative_local_styles, duration_ms, and lines (lyrics).
detailed: true to get lyrics timestamps and other metadata in the result. Corresponds to ElevenLabs’ /v1/music/detailed endpoint.Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
歌曲长度(毫秒),范围 3000-600000ms
3000 <= x <= 600000180000
模型 ID
music_v1 "music_v1"
是否返回详细信息(歌词时间戳等元数据),默认 false
简单文字提示(与 compositionPlan 互斥)
"A melancholic indie folk song with acoustic guitar and soft vocals"
详细作曲计划(与 prompt 互斥,通过 /eleven/plan 生成)
随机种子
877369
强制纯器乐,仅 prompt 模式
是否严格遵守段落时长,仅 compositionPlan 模式
输出格式,格式为 codec_sampleRate_bitrate。MP3 192kbps 需要 Creator 及以上,PCM 44.1kHz 需要 Pro 及以上
mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_32000, pcm_44100, pcm_48000, ulaw_8000, alaw_8000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192 是否保存生成结果用于后续 Inpainting 编辑。仅限具备 Inpainting 权限的企业客户使用
是否使用 C2PA 签名标记 AI 生成内容。仅适用于 MP3 输出格式,会在文件中嵌入加密的 AI 生成来源证明
任务创建成功
任务 ID,用于后续查询结果