ElevenLabs Music inpainting: redo one section vs a new Sume take
ElevenLabs Music v2 and v2.5 can regenerate one section of a song in the UI. Sume cannot edit a track: write a new brief for that part and generate again.

ElevenLabs Music v2 and v2.5 support inpainting: you select a section of a generated song and regenerate only that part. Sume has no edit or inpaint call, so a fix means a new generation, or a second short track spliced in with Timeline.
What ElevenLabs documents
The capabilities page says inpainting lets you select a specific section and regenerate just that section without affecting the rest, with v2 and v2.5 supported and quality improved in v2 (read 2026-10-02). It describes the feature in the ElevenMusic interface and gives no API steps for it (read 2026-10-02). Its changelog also lists v2.5 composition plans of up to 6,132 characters and 30 lines of 200 characters (read 2026-10-02).
| Service | Regenerate one section | How |
|---|---|---|
| ElevenLabs Music v2 / v2.5 | Yes | Select the section in the ElevenMusic UI; no API steps documented |
| Sume Music Router | No | New generation from a new prompt |
Doing the same fix on Sume
Treat the song as sections. Generate the full track, listen, then write a short brief for the part you want different, and generate that as its own track. Use the prompt's section markers, like [0:20-0:30] Breakdown:, to describe where it should sit.
Then assemble in Timeline 1.0. The spine and soundtrack take whole files, and audio.parts[] slices with source_in and duration can join up to 20 gapless pieces. That lets you join the good first half with a regenerated second half.
Honest limits
The join is a cut, not a crossfade inside the music. A key or tempo mismatch will be audible, so give both briefs the same BPM, key and instruments.
Every accepted generation is billed at the fixed Music price, so a section fix costs another full generation. If section-level editing is central to your workflow, a vendor with an inpainting UI fits better.
Sources
Related posts
More in Comparisons
- ElevenLabs Music length: 3 seconds to 5 or 10 minutes vs Sume
ElevenLabs' two pages disagree on max Music length: 5 minutes on the capabilities page, 600000 ms on the Compose reference. Sume has no length field at all.
- ElevenLabs TTS output_format list vs Sume container and encoding
ElevenLabs names output_format strings like opus_48000_64 and ulaw_8000. Sume splits it into container, sample rate, bit rate and encoding, with no Opus.
- ElevenLabs Professional Voice Clone: own voice only, 24 h retry
ElevenLabs Professional Voice Cloning only accepts your own voice, needs 30 minutes of audio and a verification step. What Sume's Voices library asks instead.
- ElevenLabs use_pvc_as_ivc: what it does and Sume's voice selector
ElevenLabs' use_pvc_as_ivc flag swaps a professional voice clone for its instant version. Sume's TTS has no such switch: you pick an avatar or a voice id.
Written by Sume