Compose music

Compose a song from a prompt or a composition plan.

Query parameters

output_formatenumOptional

Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.

Request

This endpoint expects an object.

promptstringOptional<=4100 characters

A simple text prompt to generate a song from. Cannot be used in conjunction with composition_plan.

composition_planobjectOptional

A detailed composition plan to guide music generation. Cannot be used in conjunction with prompt.

music_length_msintegerOptional3000-600000

The length of the song to generate in milliseconds. Used only in conjunction with prompt. Must be between 3000ms and 600000ms. Optional - if not provided, the model will choose a length based on the prompt.

model_id"music_v1"Optional

The model to use for the generation.

seedintegerOptional0-2147483647

Random seed to initialize the music generation process. Providing the same seed with the same parameters can help achieve more consistent results, but exact reproducibility is not guaranteed and outputs may change across system updates. Cannot be used in conjunction with prompt.

force_instrumentalbooleanOptionalDefaults to false

If true, guarantees that the generated song will be instrumental. If false, the song may or may not be instrumental depending on the prompt. Can only be used with prompt.

respect_sections_durationsbooleanOptionalDefaults to true

Controls how strictly section durations in the composition_plan are enforced. Only used with composition_plan. When set to true, the model will precisely respect each section’s duration_ms from the plan. When set to false, the model may adjust individual section durations which will generally lead to better generation quality and improved latency, while always preserving the total song duration from the plan.

Controls how strictly section durations in the `composition_plan` are enforced. Only used with `composition_plan`. When set to true, the model will precisely respect each section's `duration_ms` from the plan. When set to false, the model may adjust individual section durations which will generally lead to better generation quality and improved latency, while always preserving the total song duration from the plan.

store_for_inpaintingbooleanOptionalDefaults to false

Whether to store the generated song for inpainting. Only available to enterprise clients with access to the inpainting API.

sign_with_c2pabooleanOptionalDefaults to false

Whether to sign the generated song with C2PA. Applicable only for mp3 files.

Response

The generated audio file in the format specified

1	from elevenlabs import ElevenLabs
2	from elevenlabs.environment import ElevenLabsEnvironment
3
4	client = ElevenLabs(
5	environment=ElevenLabsEnvironment.PRODUCTION
6	)
7
8	client.music.compose()

Headers

Query parameters

Request

Response

Errors