# ElevenLabs Music v2.5

ElevenLabs Music v2.5 is the text-to-music model ElevenLabs calls its most advanced, building on Music v2 with better audio quality and prompt adherence. It makes full songs with vocals or instrumentals from a written prompt. In Sloosh it runs in Spacelab's Music & Sound node, making tracks from 3 seconds to 1 minute long.

Web page: https://sloosh.ai/models/elevenlabs-music-v2.5

[How to use ElevenLabs Music v2.5](https://sloosh.ai/docs/models#audio-models)

## Key facts in Sloosh

|   |   |
| --- | --- |
| Made by | ElevenLabs |
| Where | Spacelab, Music & Sound node (not in Studio) |
| Makes | audio: music, with vocals or instrumental (MP3) |
| Inputs | text prompt; Instrumental switch |
| Length | 3 to 60 seconds (quick picks 15, 30, 60) |
| Prompt limit | 4,100 characters |
| Reference images | none |
| Lyrics input | no (lyrics port hidden for this model) |

## Best for

- Short music beds for product reels and ads, from 3 seconds to a minute (Sloosh catalog; ElevenLabs calls the music "cleared for nearly all commercial uses", ElevenLabs docs: Music).
- Vocal-led or acoustic tracks: ElevenLabs says v2.5 was the preferred take most of the time across 47,885 blind pairs, with the widest gap in vocal-led and acoustic genres (ElevenLabs blog: Music v2.5, company-reported).
- Instrumental-only beds behind a voiceover, using the node's Instrumental switch.

## How to use ElevenLabs Music v2.5 in Sloosh

1. Open Spacelab ([sloosh.ai/spacelab](https://sloosh.ai/spacelab)) and add a Music & Sound node from the add-node flyout (Audio).
2. In the node's Model picker, choose ElevenLabs Music v2.5.
3. Wire a Prompt or Text Input node into the node's prompt describing the track. Set Duration (3 to 60 seconds) and turn Instrumental on for a track with no vocals.
4. Run the node. The exact price shows in Spacelab before you run.
5. Wire the audio output into Merge audio + video to put it under a clip, or into a Download node.

## ElevenLabs Music v2.5 prompting tips

- Name the genre, mood, tempo and lead instruments in the prompt; the Spacelab node docs suggest this for every music model.
- Say "instrumental" or use the Instrumental switch when the track sits under speech.
- Do not build the prompt on another artist's song: ElevenLabs blocks downloads of tracks built on another artist's song in its own app (ElevenLabs blog: Music v2.5).
- Decide genre, mood, instruments, tempo and era up front, or the model picks the most average choice (ElevenLabs docs: Music best practices).
- State BPM and key, for example "130 BPM, in A minor" (ElevenLabs docs: Music best practices).
- Describe the arrangement in order with "start with", "then", "bring in" (ElevenLabs docs: Music best practices).

## ElevenLabs Music v2.5 example prompts

**Prompt 1**

```text
Upbeat indie pop with hand claps and bright acoustic guitar, 118 BPM, cheerful and light, instrumental, for a 30-second skincare reel.
```

**Prompt 2**

```text
Warm lo-fi hip hop beat with soft vinyl crackle, mellow Rhodes chords and a lazy drum groove, no vocals, background for a coffee brand video.
```

**Prompt 3**

```text
Short upbeat jingle with a female vocal singing "fresh every morning", bright synths and a punchy kick, 15 seconds.
```

## How it compares in Sloosh

| Model | Length in Sloosh | Lyrics input | Reference images | Instrumental switch |
| --- | --- | --- | --- | --- |
| ElevenLabs Music v2.5 | 3 to 60 s | no | no | yes |
| MiniMax Music 3 | 1 to 300 s | yes | no | yes |
| [Lyria 3 Clip](https://sloosh.ai/models/lyria) | fixed 30 s | no | up to 10 | no |
| [Lyria 3.5](https://sloosh.ai/models/lyria) | full song (not settable) | no | up to 10 | no |

All figures from Sloosh's catalog rows. For a sound effect rather than music, see ElevenLabs Sound Effects v2.

## Where else it runs

- ElevenMusic, ElevenCreative and the ElevenLabs API (ElevenLabs blog: Music v2.5, Sept 2026).

## Frequently asked questions

### What is ElevenLabs Music v2.5?

ElevenLabs' music model that builds on Music v2 with improved audio quality and prompt adherence (ElevenLabs docs). In Sloosh it is one of the models in Spacelab's Music & Sound node.

### How long can a track be in Sloosh?

From 3 to 60 seconds, set in the node's Duration field.

### Can it make instrumentals?

Yes. Turn on the Instrumental switch in the Music & Sound node.

### Can I give it my own lyrics in Sloosh?

No. The lyrics port is hidden for this model; MiniMax Music 3 takes lyrics.

### How do I put the music on a video?

Wire the Music & Sound output and your video into Merge audio + video, which replaces the video's sound and keeps the video's length.

## Related

- Models: [ElevenLabs Sound Effects v2](https://sloosh.ai/models/elevenlabs-sound-effects-v2), MiniMax Music 3, [Lyria 3 Clip](https://sloosh.ai/models/lyria), [Lyria 3.5](https://sloosh.ai/models/lyria)
- Spaces: [Add a soundtrack](https://sloosh.ai/spaces/add-a-soundtrack)
- Docs: [Models](https://sloosh.ai/docs/models.md#audio-models), [Edit nodes](https://sloosh.ai/docs/nodes-edit.md#merge-audio-video)

## Sources

- [ElevenLabs docs: Music best practices](https://elevenlabs.io/docs/overview/capabilities/music/best-practices)
- [Sloosh docs: Models (Audio models table)](https://sloosh.ai/docs/models.md)
- [Sloosh docs: Generate nodes](https://sloosh.ai/docs/nodes-generate.md)
- [Sloosh docs: Edit nodes (Merge audio + video)](https://sloosh.ai/docs/nodes-edit.md)
- [ElevenLabs docs: Music](https://elevenlabs.io/docs/capabilities/music)
- [ElevenLabs blog: Music v2.5](https://elevenlabs.io/blog/music-v2-5-model)
- [ElevenLabs docs: Models](https://elevenlabs.io/docs/overview/models)