ElevenLabs Music Generator

Generate studio-grade AI music with elevenlabs-music-v1. One model exposes three generation modes selected by promptObject.mode:

Prompt — describe the song in natural language and set a target length.
Composition Plan — control individual sections, lyrics placement, and per-section styles.
Video — generate background music synced to a source video.

Supported Models

elevenlabs-music-v1 — ElevenLabs Music V1

Parameters

Parameter	Type	Required	Description
`type`	string	Yes	Must be `"MUSIC_GENERATOR"`
`model`	string	Yes	Must be `"elevenlabs-music-v1"`
`promptObject`	object	Yes	Mode-specific parameters (see below)

Common `promptObject` fields (all modes)

Field	Type	Required	Description
`mode`	string (enum)	Yes	Generation mode discriminator. One of `prompt`, `composition_plan`, `video`
`output_format`	string (enum)	Yes	Audio output format. One of 21 formats (see table below). Default `mp3_44100_128`
`sign_with_c2pa`	boolean	No	Sign output with C2PA content credentials. Default `false`

Prompt mode (`mode: "prompt"`)

Field	Type	Required	Description
`prompt`	string	Yes	Describe the song you want — mood, instruments, tempo, vibe...
`music_length_ms`	integer	Yes	Target length in milliseconds. min 3000, max 600000 (3s – 10min)
`force_instrumental`	boolean	No	Force an instrumental track (no vocals). Default `false`

Composition Plan mode (`mode: "composition_plan"`)

Field	Type	Required	Description
`composition_plan`	object	Yes	Full song plan with global styles and ordered sections (see nested table)
`respect_sections_durations`	boolean	No	Respect the per-section `duration_ms` values exactly. Default `false`
`seed`	integer	No	Reproducibility seed. min 0, max 2147483647. Accepted but not currently forwarded in plan mode

`composition_plan` object

Field	Type	Required	Description
`positive_global_styles`	string[]	Yes	Styles and musical directions that should be present in the entire song. min 1 item. Use English for best results.
`negative_global_styles`	string[]	Yes	Styles and musical directions that should not be present in the entire song. min 1 item. Use English for best results.
`sections`	object[]	Yes	Ordered song sections (see nested table). min 1 item

`composition_plan.sections[]` object

Field	Type	Required	Description
`section_name`	string	Yes	Name of the section (e.g. `Verse 1`, `Chorus`). 1–100 chars
`positive_local_styles`	string[]	Yes	Styles that should be present in this section
`negative_local_styles`	string[]	Yes	Styles that should not be present in this section
`duration_ms`	integer	Yes	Section duration in milliseconds. min 3000, max 120000
`lines`	string[]	Yes	Lyric lines for this section. Each line ≤ 200 chars

Video mode (`mode: "video"`)

Field	Type	Required	Description
`video_url`	string	Yes	Source video asset key — S3 asset key (upload via the asset API first)
`description`	string	No	Optional natural-language description. ≤ 1000 chars
`tags`	string[]	No	Optional style tags. ≤ 10 items

Source video file limits (enforced at upload time): ≤ 200 MB, ≤ 600 seconds.

Output Format Options

All 21 values accepted by the API. Default is mp3_44100_128.

Value	Container	Description
`mp3_22050_32`	mp3	MP3, 22.05 kHz, 32 kbps
`mp3_24000_48`	mp3	MP3, 24 kHz, 48 kbps
`mp3_44100_32`	mp3	MP3, 44.1 kHz, 32 kbps
`mp3_44100_64`	mp3	MP3, 44.1 kHz, 64 kbps
`mp3_44100_96`	mp3	MP3, 44.1 kHz, 96 kbps
`mp3_44100_128`	mp3	MP3, 44.1 kHz, 128 kbps
`mp3_44100_192`	mp3	MP3, 44.1 kHz, 192 kbps
`pcm_8000`	wav	PCM, 8 kHz (wrapped as `.wav`)
`pcm_16000`	wav	PCM, 16 kHz (wrapped as `.wav`)
`pcm_22050`	wav	PCM, 22.05 kHz (wrapped as `.wav`)
`pcm_24000`	wav	PCM, 24 kHz (wrapped as `.wav`)
`pcm_32000`	wav	PCM, 32 kHz (wrapped as `.wav`)
`pcm_44100`	wav	PCM, 44.1 kHz (wrapped as `.wav`)
`pcm_48000`	wav	PCM, 48 kHz (wrapped as `.wav`)
`ulaw_8000`	wav	μ-law, 8 kHz (wrapped as `.wav`)
`alaw_8000`	wav	A-law, 8 kHz (wrapped as `.wav`)
`opus_48000_32`	opus	Opus, 48 kHz, 32 kbps
`opus_48000_64`	opus	Opus, 48 kHz, 64 kbps
`opus_48000_96`	opus	Opus, 48 kHz, 96 kbps
`opus_48000_128`	opus	Opus, 48 kHz, 128 kbps
`opus_48000_192`	opus	Opus, 48 kHz, 192 kbps

Interactive API Testing

API Playground

https://api.1min.ai/api/features

AI Model *

Generation mode *

Output Format *

Composition plan *

Positive global styles *

popenergetic

Negative global styles

slow

Section 1

Section name * (max 100)Duration (ms) * (3000–120000)Positive local styles *

ambient

Negative local styles *

heavy

Lyrics * (max 200 chars / line)

Section 2

Section name * (max 100)Duration (ms) * (3000–120000)Positive local styles *

rock

Negative local styles *

quiet

Lyrics * (max 200 chars / line)

Respect sections durations

Sign with C2PA

Generated cURL Command:

curl -X POST "https://api.1min.ai/api/features" \
  -H "API-KEY: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
  "type": "MUSIC_GENERATOR",
  "model": "elevenlabs-music-v1",
  "conversationId": "MUSIC_GENERATOR",
  "promptObject": {
    "mode": "composition_plan",
    "output_format": "mp3_44100_128",
    "sign_with_c2pa": false,
    "composition_plan": {
      "positive_global_styles": [
        "pop",
        "energetic"
      ],
      "negative_global_styles": [
        "slow"
      ],
      "sections": [
        {
          "section_name": "Intro",
          "positive_local_styles": [
            "ambient"
          ],
          "negative_local_styles": [
            "heavy"
          ],
          "duration_ms": 10000,
          "lines": [
            ""
          ]
        },
        {
          "section_name": "Chorus",
          "positive_local_styles": [
            "rock"
          ],
          "negative_local_styles": [
            "quiet"
          ],
          "duration_ms": 20000,
          "lines": [
            "We rise again"
          ]
        }
      ]
    },
    "respect_sections_durations": false
  }
}'

Response Format

Successful requests return an aiRecord echoing the submitted promptObject and a resultObject containing the uploaded audio file path. For Video mode, temporaryUrlList also includes a playback URL for the source video.

{
  "aiRecord": {
    "uuid": "9f4a2b1e-6c3d-4f5e-9a8b-2d1c0e3f4a5b",
    "userId": "c937fbcc-fa8f-4565-a440-c4d87f56fcb2",
    "teamId": "a4e176b2-dabb-451e-9c58-62b451fa9630",
    "model": "elevenlabs-music-v1",
    "type": "MUSIC_GENERATOR",
    "status": "SUCCESS",
    "createdAt": "2026-05-27T10:52:19.827Z",
    "aiRecordDetail": {
      "promptObject": {
        "mode": "composition_plan",
        "output_format": "mp3_44100_128",
        "sign_with_c2pa": false,
        "composition_plan": {
          "positive_global_styles": ["pop", "energetic"],
          "negative_global_styles": ["slow"],
          "sections": [
            {
              "section_name": "Intro",
              "positive_local_styles": ["ambient"],
              "negative_local_styles": ["heavy"],
              "duration_ms": 10000,
              "lines": [""]
            },
            {
              "section_name": "Chorus",
              "positive_local_styles": ["rock"],
              "negative_local_styles": ["quiet"],
              "duration_ms": 20000,
              "lines": ["We rise again"]
            }
          ]
        },
        "respect_sections_durations": false
      },
      "resultObject": [
        "development/audios/2026_05_27_17_52_25_414_538984.mp3"
      ],
    },
    "temporaryUrl": ""
  }
}

Example Requests

Prompt mode

{
  "type": "MUSIC_GENERATOR",
  "model": "elevenlabs-music-v1",
  "promptObject": {
    "mode": "prompt",
    "output_format": "mp3_44100_128",
    "prompt": "Upbeat synthwave with a driving bassline and bright arpeggios",
    "music_length_ms": 30000,
    "force_instrumental": false,
    "seed": 42,
    "sign_with_c2pa": false
  }
}

Composition Plan mode

{
  "type": "MUSIC_GENERATOR",
  "model": "elevenlabs-music-v1",
  "promptObject": {
    "mode": "composition_plan",
    "output_format": "mp3_44100_128",
    "sign_with_c2pa": false,
    "composition_plan": {
      "positive_global_styles": ["pokemon"],
      "negative_global_styles": ["superman"],
      "sections": [
        {
          "section_name": "Picachu",
          "positive_local_styles": ["rock"],
          "negative_local_styles": ["roll"],
          "duration_ms": 120000,
          "lines": ["helo helo"]
        },
        {
          "section_name": "good bye",
          "positive_local_styles": ["slow"],
          "negative_local_styles": ["query"],
          "duration_ms": 10000,
          "lines": ["one two three 100"]
        }
      ]
    },
    "respect_sections_durations": false,
    "seed": 1
  }
}

Each section's duration_ms must be between 3000 and 120000. Total audio length is the sum of all section durations.

Video mode

Upload the source video to the asset API first; pass the returned S3 key as video_url.

{
  "type": "MUSIC_GENERATOR",
  "model": "elevenlabs-music-v1",
  "promptObject": {
    "mode": "video",
    "output_format": "mp3_44100_128",
    "video_url": "development/videos/2026_05_27_12_31_05_a1b2c3.mp4",
    "description": "Cinematic, suspenseful orchestral score that builds toward the final shot",
    "tags": ["cinematic", "orchestral", "suspense"],
    "sign_with_c2pa": false
  }
}

Use Cases

🎬 Film & video scoring — Generate custom soundtracks synced to your footage.
📢 Commercial content — Create music for ads, social media, podcasts, and marketing campaigns.
🎵 Music production — Compose original songs with vocals, instrumentals, or a cappella tracks.
🎮 Game audio — Produce dynamic background music for games and interactive experiences.
📱 App soundscapes — Generate ambient and branded audio for applications.
🎙️ Podcast branding — Create unique intros, outros, and transition music.

Supported Models​

Parameters​

Common promptObject fields (all modes)​

Prompt mode (mode: "prompt")​

Composition Plan mode (mode: "composition_plan")​

composition_plan object​

composition_plan.sections[] object​

Video mode (mode: "video")​

Output Format Options​

Interactive API Testing​