Home / Servers / ElevenLabs API / compose_detailed
Compose Music With A Detailed Response
An MCP tool from the ElevenLabs API server, hosted on mcp.hjlabs.in.
Compose Music With A Detailed Response Compose a song from a prompt or a composition plan. [POST /v1/music/detailed]
Name on the gateway: elevenlabs_api__compose_detailed · may change things.
Parameters
| Name | Type | Description |
|---|---|---|
output_format | string | Output format of the generated audio. Formatted as codec_sample_rate_bitrate.… |
enable_logging | boolean | When enable_logging is set to false zero retention mode will be used for the… |
prompt | string | A simple text prompt to generate a song from. Cannot be used in conjunction… |
generation_mode | track | loop | ambience | video_to_music | Optional generation mode hint for prompt-based music generation. Can only be… |
music_prompt | object | A music prompt. Deprecated. Use composition_plan instead. |
lyrics_text | string | The lyrics text to use for the generation. |
composition_plan | object | A detailed composition plan to guide music generation. Cannot be used in… |
music_length_ms | integer | The length of the song to generate in milliseconds. Used only in conjunction… |
model_id | music_v1 | music_v2 | music_v2_5 | The model to use for the generation. |
seed | integer | Random seed to initialize the music generation process. Providing the same… |
force_instrumental | boolean | If true, guarantees that the generated song will be instrumental. If false… |
finetune_id | string | The ID of the finetune to use for the generation |
finetune_strength | number | How strongly the finetune influences the generation. Defaults to 1.0 (full… |
use_phonetic_names | boolean | If true, proper names in the prompt will be phonetically spelled in the lyrics… |
respect_sections_durations | boolean | Controls how strictly section durations in the composition_plan are enforced.… |
store_for_inpainting | boolean | Whether to store the generated song for inpainting. |
with_timestamps | boolean | Whether to return the timestamps of the words in the generated song. |
with_waveform_visual | boolean | Whether to return the visual waveform of the generated song. |
sign_with_c2pa | boolean | Whether to sign the generated song with C2PA. Applicable only for mp3 files. |
model_style_prefix | music | sfx | Model Style Prefix |
How to call it
Through the Smart Gateway, any client can run it by name with call_tool, or let the gateway find it with search_tools:
{
"name": "elevenlabs_api__compose_detailed",
"arguments": {}
}Or connect the ElevenLabs API server directly, which lists 487 tools including this one:
claude mcp add --transport http hj-elevenlabs-api https://mcp.hjlabs.in/mcp/elevenlabs-api \
--header "Authorization: Bearer YOUR_API_KEY"Try asking
Use the compose music with a detailed response tool with output_format set to ….