MAINTENANCE · 15 FORMATS · SCHEMA 1.0

Format Changelog

Every brief here targets a specific set of input fields on a specific model. When a platform changes what it accepts, the format is revised, the date moves, and the change is listed below — so you can see how current the thing you are relying on actually is.

Current formats

Dates show the last revision of the format description, not the platform's release date.

EngineModel / versionFields briefedRevised
Eleven Musicelevenlabs_musicPrompt · composition plan2026-10-22
Sunov6Style · lyrics · exclude styles · two sliders2026-11-10
UdioudioDescribe · lyrics · seed · clarity2026-11-10
MurekaV9.5Prompt · styles · lyrics2026-11-10
MiniMax MusicMusic 3Prompt · section-tagged lyrics · flags2026-11-10
YuE2YuE2-3BLyrics · style prompt · genre tag2026-11-10
Soundversev9Describe (≤500) · tags · lyrics2026-11-10
TrebloMelodia v3Prompt · tags · lyrics · prompt strength2026-11-10
Stable Audio2.5Prompt · steps · CFG · seed2026-10-22
Soundraw—Genre · mood · tempo · length2026-10-22
Mubert—Prompt · tags · track/stream mode2026-10-22
Beatoven—Mood session · timeline edits2026-10-22
AIVA—Style preset · key and tempo · editor passes2026-10-22
LoudlyMANTA 1 / VEGAStyle (≤1000) · lyrics (≤3000) · vocal gender · instrumental flag2026-11-10
MusicGenAudioCraft largeDescription · model size · sampling parameters2026-11-10

Formats are reviewed when a platform ships a model or field change, and whenever one of our own briefs is corrected. A correction is never made quietly: it lands here with a date.

History

Developer payload schema

The API JSON view returns one object per engine. The schema string is stable within a major version, and fields are only ever added — so a script that pins the schema keeps working.

{ "schema": "musicdna.brief/1.0", "brief_id": "mdna_7f3a91c2", "generated_at": "2026-11-10T12:00:00.000Z", "engine": { "id": "suno", "name": "Suno", "version": "v6", "model": "suno-v6", "url": "https://suno.com/" }, "source": { "bpm": 104, "key": "F# minor", "key_confidence": 0.71, "brightness": 0.62, "dynamics": 0.48, "syncopation": 0.33, "duration_seconds": 187, "genres": ["Indie Pop"], "moods": ["Warm", "Nostalgic"], "instruments": ["guitar", "drums"] }, "model_engine": "suno-v6", "api_parameters": { "...": "per-engine fields" } }

brief_id is derived from the measurements and the engine, so the same analysis of the same file returns the same id — useful for de-duplicating a batch without storing the audio. source carries the measured facts, so a pipeline can re-derive a brief without re-running the browser analysis. model_engine is retained from schema 1.0's first release and will not move.

Where this is enforced

The same commitments appear in the Trust & Content Policy: text only, no audio output, no sampling, no voice models, no artist or song matching. A format change cannot cross those lines, whatever a platform adds.

See The Current Formats

Open the Studio, drop a reference, and pick an engine — the brief you get is the one described in this table.

OPEN THE STUDIO →