ElevenLabs Music terms: restricted industries and banned inputs
Before an ad brief goes into ElevenLabs Music: the terms list restricted industries and prompt inputs you cannot send. What Sume does and does not enforce.

Yes, check the ElevenLabs music terms before you brief an ad, because they go beyond a generic commercial-use line. As read on 2026-10-04, the Music terms restrict use by companies in firearms, tobacco, pharmaceuticals, adult entertainment, religious organizations and political advocacy, and they bar prompts that contain artist, songwriter, song, album or label names or substantial lyrics. A brand in one of those sectors should read them first.
What the terms page says
Two lists matter to a buyer. The first is about who may use the service. The second is about what you may type into the prompt box or API field. A reference-heavy brief such as "in the style of [artist]" breaks the second list before any audio exists, and a sector rule can apply to the whole account regardless of how clean the prompt is.
The same page says output "may not be unique and may be similar or identical to Output returned to other users", that the service is provided as is, and that Model-Specific Terms override Service Terms. ElevenLabs reserves the right to adjust pricing, saying it will use commercially reasonable efforts to notify customers in advance, and may pass through fees attributable to its third-party licensors.
| Topic | What the page says | What to do in a brief |
|---|---|---|
| Restricted sectors | Firearms, tobacco, pharmaceuticals, adult entertainment, religious organizations, political advocacy | Ask the vendor in writing if your advertiser is near the line |
| Forbidden inputs | Artist, songwriter, song, album, publisher or label names; substantial lyrics | Describe tempo, mood and instruments instead |
| Uniqueness | Output may be similar or identical to what other users receive | Do not promise a client an exclusive track |
| Precedence | Model-Specific Terms over Service Terms over the underlying agreement | Read the music page, not only the general terms |
How this maps to the Sume Music Router
Sume's Music Router takes a prompt of 1 to 5000 characters and, by default, routes to Lyria 3.5. Sume docs for the router do not list an industry exclusion table, and Sume does not forward ElevenLabs terms to you, because the router does not call ElevenLabs. Your rights for a Sume track depend on the terms that apply to Sume and to the engine that rendered it. Read job.request.routed_model on the finished job so you know which engine that was.
The practical overlap is the brief itself. The Music 1.0 page says to revise flagged content while keeping the musical brief, and to put exclusions in the positive prompt, since a non-empty negative_prompt returns a 400. A brief written from the seven axes (emotion, genre lineage, tempo, key, instruments, arc, era) carries no artist names, so it avoids the artist-name part of the ElevenLabs input list as a side effect.
A pre-flight list
Run this before the first generation of a campaign:
- Name the advertiser's sector and compare it with the restricted list on the vendor page.
- Strip artist, song, album and label names from every brief, and do not paste lyrics.
- Decide whether the client needs an exclusive track. If yes, no generator page we read promises one.
- Record the engine, plan and date in the job
metadata, which Sume stores on the job and does not send to the provider. - Re-read the page on the day you ship: terms change, and this one is a summary of one reading.
What this post does not settle
It is not legal advice. The page was read once on 2026-10-04 and summarised here, so quote the live text, not this post, in a client contract. For job polling and result fields, see Jobs and results. The ElevenLabs API docs page, also read the same day, points developers back to the music terms for plan-specific details, which is another reason to treat the terms page as the source of truth.
Sources
Related posts
More in Comparisons
- ElevenLabs TTS on fal at $0.10 per 1,000 characters vs direct and Sume
fal lists ElevenLabs TTS at $0.10 per 1,000 characters, ElevenLabs lists $0.08 for v3, Sume is $0.0475. A 2,000-character script: $0.20, $0.16, $0.095.
- fal image model list vs the Sume catalog: how to check by query
fal.ai lists Seedream 5.0, GPT Image 2.5, Flux 2, Nano Banana 2, Ideogram 4 and Krea 2. How to see which ones a Sume key can call, with a short Python script.
- fal retry budgets and 1-hour grace vs Sume job error categories
fal's changelog lists per-condition retry budgets and termination grace of up to one hour. Sume job errors carry a category, a next action and retry-after.
- fal's Usage API vs Sume's per-job, per-run cost reads
fal's changelog lists a Usage API for cost attribution. Sume's GET /v1/usage filters by job_id, run_id or thread_id and returns a summary. How to attribute.
Written by Sume