curl -X POST 'https://api.elevenlabs.io/v1/music/stream?output_format=auto' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "prompt": "string",
  "generation_mode": "track",
  "music_prompt": {
    "negative_global_styles": [
      "metal",
      "hip-hop",
      "country"
    ],
    "positive_global_styles": [
      "pop",
      "rock",
      "jazz"
    ],
    "sections": [
      {
        "duration_ms": 10000,
        "lines": [
          "Verse 1 lyrics"
        ],
        "negative_local_styles": [
          "metal",
          "hip-hop",
          "country"
        ],
        "positive_local_styles": [
          "pop",
          "rock",
          "jazz"
        ],
        "section_name": "Verse 1"
      }
    ]
  },
  "lyrics_text": "string",
  "composition_plan": {
    "negative_global_styles": [
      "metal",
      "hip-hop",
      "country"
    ],
    "positive_global_styles": [
      "pop",
      "rock",
      "jazz"
    ],
    "sections": [
      {
        "duration_ms": 10000,
        "lines": [
          "Verse 1 lyrics"
        ],
        "negative_local_styles": [
          "metal",
          "hip-hop",
          "country"
        ],
        "positive_local_styles": [
          "pop",
          "rock",
          "jazz"
        ],
        "section_name": "Verse 1"
      }
    ]
  },
  "music_length_ms": 0,
  "model_id": "music_v1",
  "seed": 0,
  "force_instrumental": false,
  "finetune_id": "string",
  "finetune_strength": 1,
  "use_phonetic_names": false,
  "store_for_inpainting": false
}'

# POST /v1/music/stream (ElevenLabs API)
Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03

> Stream Composed Music

## Critical Gotchas
* Authentication uses the non-standard `xi-api-key` header, not `Authorization: Bearer`. Sending a Bearer token returns HTTP 401.
* Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (`--output speech.mp3`) rather than parsing it.

## cURL
curl -X POST 'https://api.elevenlabs.io/v1/music/stream?output_format=auto' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"prompt":"string","generation_mode":"track"}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| output_format | query | string | No | Output format of the generated audio.... |
| prompt | body | string | No | A simple text prompt to generate a so... |
| generation_mode | body | string | No | Optional generation mode hint for pro... |

## Response (200 OK)
"binary"

---
Need an API key? Get one at https://elevenlabs.io/app/sign-up

POST

/v1/music/stream

ElevenLabs API

Stream Composed Music

Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03 · upstream hash matched

Actions

Agents: curl -H "Accept: text/markdown" this URL
→ 214 tokens · Vary: Accept

Critical gotchas

Authentication uses the non-standard xi-api-key header, not Authorization: Bearer. Sending a Bearer token returns HTTP 401.

Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (--output speech.mp3) rather than parsing it.

cURL

curl -X POST 'https://api.elevenlabs.io/v1/music/stream?output_format=auto' \  -H "xi-api-key: $ELEVENLABS_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "prompt": "string",  "generation_mode": "track",  "music_prompt": {    "negative_global_styles": [      "metal",      "hip-hop",      "country"    ],    "positive_global_styles": [      "pop",      "rock",      "jazz"    ],    "sections": [      {        "duration_ms": 10000,        "lines": [          "Verse 1 lyrics"        ],        "negative_local_styles": [          "metal",          "hip-hop",          "country"        ],        "positive_local_styles": [          "pop",          "rock",          "jazz"        ],        "section_name": "Verse 1"      }    ]  },  "lyrics_text": "string",  "composition_plan": {    "negative_global_styles": [      "metal",      "hip-hop",      "country"    ],    "positive_global_styles": [      "pop",      "rock",      "jazz"    ],    "sections": [      {        "duration_ms": 10000,        "lines": [          "Verse 1 lyrics"        ],        "negative_local_styles": [          "metal",          "hip-hop",          "country"        ],        "positive_local_styles": [          "pop",          "rock",          "jazz"        ],        "section_name": "Verse 1"      }    ]  },  "music_length_ms": 0,  "model_id": "music_v1",  "seed": 0,  "force_instrumental": false,  "finetune_id": "string",  "finetune_strength": 1,  "use_phonetic_names": false,  "store_for_inpainting": false}'

Get a free ElevenLabs API key → sponsored

Parameters

Name	In	Type	Required	Description
output_format	query	string	No	Output format of the generated audio. Formatted as codec_sample_rate_bitrate. Use "auto" (the default) to let the API pick the best format for the selected model: mp3_44100_128 for v1 models and mp3_48000_192 for v2 models.
prompt	body	string	No	A simple text prompt to generate a song from. Cannot be used in conjunction with `composition_plan`.
generation_mode	body	string	No	Optional generation mode hint for prompt-based music generation. Can only be used with `prompt`.
music_prompt	body	object	No	A music prompt. Deprecated. Use `composition_plan` instead.
lyrics_text	body	string	No	The lyrics text to use for the generation.
composition_plan	body	object	No	A detailed composition plan to guide music generation. Cannot be used in conjunction with `prompt`.
music_length_ms	body	integer	No	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	body	string	No	Request body field model_id.
seed	body	integer	No	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_instrumental	body	boolean	No	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`.
finetune_id	body	string	No	The ID of the finetune to use for the generation
finetune_strength	body	number	No	How strongly the finetune influences the generation. Defaults to 1.0 (full strength). Lower values soften the influence of the finetune, leaving more room for prompt-level steering. Only meaningful when `finetune_id` is also provided.
use_phonetic_names	body	boolean	No	If true, proper names in the prompt will be phonetically spelled in the lyrics for better pronunciation by the music model. The original names will be restored in word timestamps.
store_for_inpainting	body	boolean	No	Whether to store the generated song for inpainting.

Response 200 OK

"binary"