Workflow

Add an Instrument Layer

Add a new instrument part, such as a funk bassline or a string section, to an existing song. Soundverse analyzes the song's structure, generates the instrument in the requested style from your track, and merges it onto the original starting at the first verse.

Dedicated route only

This workflow uses POST /v1/instrument-layers. It runs a fixed multi-step pipeline; there is no generic tool_id for it.

Quickstart

POST/v1/instrument-layersadd an instrument layer

curl -X POST https://apiv2.soundverse.ai/v1/instrument-layers \ -H "Authorization: Bearer sksoundverse_..." \ -H "Content-Type: application/json" \ -H "Idempotency-Key: instrument-layer-001" \ -d '{ "song_file_id": "018f0000-0000-7000-8000-000000000002", "instrument_brief": "funk bassline", "license": "royalty_free" }'

The song_file_id must be an active uploaded audio file owned by the authenticated enterprise account.

Getting a song_file_id

Upload the file first via POST /v1/files — either {"source_url": "..."} if you already host it, or a multipart/form-data file part to upload bytes directly. Both return a file_id owned by your account, ready to pass here.

Request fields

FieldTypeRequiredDefaultDescription
song_file_iduuidYes—ID of the song to add the instrument layer to, an audio file owned by the authenticated enterprise account (upload it first via POST /v1/files). Maximum 60 MiB.
instrument_briefstringYes—The instrument layer to add and its style. Name one of drums, bass, guitar, keyboard, percussion, strings, synth, brass, FX, plus how it should sound (e.g. 'funk bassline', 'guitar solo in Slash style'). The generated part is aligned to the first verse detected in the track.
licenselicense tierNo"royalty_free"License tier to price and attach to every step of the pipeline.

How it works

Each request runs 5 steps in order:

  1. Analyzing the track’s structure (intro, verses, choruses, bridge, outro).
  2. Generating the requested instrument stem from the uploaded track.
  3. Trimming the new instrument part so it ends with the song.
  4. Merging the new instrument stem onto the original, aligned at the first verse.
  5. Rendering the layered song into one playable file.

Progress streams over GET /v1/generations/{task_id}/stream as each step starts and finishes.

Notes

The new instrument part is generated from your track, enters at the first verse found by the section analysis, and is trimmed so the finished song ends when your original does.

Results and playback

Poll GET /v1/generations/{task_id} until the task is completed. The finished result is added to the authenticated account’s Soundverse Library. Enterprise API outputs are hidden from public/profile surfaces by default.

For API-only download, resolve the output’s file_id with GET /v1/files/{file_id}/url and use the returned short-lived signed URL.

Pricing

This workflow is priced pass-through: you are billed for each step the pipeline runs, at that step’s enterprise rate, in the license tier you requested. The pipeline itself adds no separate fee, and your billing ledger shows one entry per step. The steps that carry the cost are:

  • Section analysis
  • Instrument stem generation
  • Duration trim
  • Mixing
  • Final render

There is no fixed per-request price; the total depends on the input and on which optional steps run.