Music
The model you name decides how a song is made; the three kinds differ in output and in whether lyrics are required.
Available music models
| Model | Pipeline | Output | Size | Parts | Registries |
|---|
The same catalog dppan models --music reads; it also shows what is installed and, for a partial install, what is missing.
| Output | Lyrics | Separate tracks | |
|---|---|---|---|
minimax | 44.1 kHz stereo | optional | no |
acestep | 48 kHz stereo | optional | no |
yue | 16 kHz mono | required | vocal / instrumental |
Read the sample rate and channels from the response rather than assuming them.
Getting a music model
A music model is four or five files in one directory. MiniMax-Music3:
BUNDLE=~/.dppan/models/bundles/minimax-music3
# The language model comes from a different repository.
dppan pull hf:Serveurperso/MiniMax-Music3-GGUF:Q8_0 --component language_model --out $BUNDLE
# The other four. --f16 halves the transformer; see below.
dppan pull hf:audio-cpp/MiniMax-Music3-GGUF:BF16 --component transformer --f16 --out $BUNDLE
dppan pull hf:audio-cpp/MiniMax-Music3-GGUF:Q8_0 --component rvq_depth_decoder --out $BUNDLE
dppan pull hf:audio-cpp/MiniMax-Music3-GGUF --component condition_encoder --out $BUNDLE
dppan pull hf:audio-cpp/MiniMax-Music3-GGUF --component vocoder --out $BUNDLE
dppan-orchestratorAbout 20 GB, or 15 GB with --f16. The orchestrator serves it on its next start.
Pass the same
--outevery time. Without it, each pull lands in a directory named after its own repository, and no directory holds a whole model.Component names are the publisher's, exactly as written:
condition_encoder, notcondition-encoder. A wrong name lists the right ones:no component matches "condition-encoder"; repo has: CONDITION_ENCODER, LANGUAGE_MODEL, RVQ_DEPTH_DECODER, TRANSFORMER, VOCODERName the quant (
:Q8_0) where a component has several.YuE needs all three of its components before it is recognised.
ACE-Step:
pullwrites a second copy of its text encoder beside the original. Keep both.
Models are found under ~/.dppan/models/bundles at startup. To keep them elsewhere, list the directories:
DPPAN_MUSIC_BUNDLE=/vol/a,/vol/b dppan-orchestratorStartup logs what it found and why it skipped anything — an incomplete directory names its missing components. A model shown in the dashboard can make a song.
Smaller and faster: --f16
--f16 converts an unquantised component to F16 as it installs: MiniMax's 9.1 GiB transformer becomes half that, and a song takes about half as long. It is lossy, so it is opt-in; already-quantised components are skipped.
To convert a component already on disk, delete it and pull it again with --f16:
rm ~/.dppan/models/bundles/minimax-music3/transformer_bf16.gguf
dppan pull hf:audio-cpp/MiniMax-Music3-GGUF:BF16 --component transformer --f16 \
--out ~/.dppan/models/bundles/minimax-music3Do delete the original: two copies of one component leave the choice to chance.
Generating
curl http://localhost:8080/v1/audio/music \
-H 'content-type: application/json' \
-d '{"model":"minimax-music3","input":"warm lo-fi hip hop, dusty piano, vinyl crackle",
"lyrics":"[verse]\nlate night on an empty street\n",
"duration_seconds":30}' --output song.wav| Field | |
|---|---|
model | The model, named by its directory |
input | The style: genre, instruments, mood, tempo. Detail helps |
lyrics | Optional for minimax and acestep; required for yue, with [verse] / [chorus] headers. Leave it out for an instrumental |
duration_seconds | Clamped to the deployment's ceiling |
steps | Solver steps. Lower is faster and blurs the words |
stems | mix (default), vocal, or instrumental |
response_format | wav only |
minimax-music3, 20 seconds (the ceiling raised as in Length), from a style of catchy synth-pop at 118 BPM with a clear female lead vocal, and lyrics.Expect this request to time out. A song takes minutes, so the wait usually ends with a job ID to poll on /v1/generations/{id}. For anything but a short clip, use the job API directly.
Vocals or backing track alone
YuE can return the vocals or the instrumental alone at no extra cost:
curl http://localhost:8080/v1/audio/music \
-H 'content-type: application/json' \
-d '{"model":"yue-s1-s2-en-cot","input":"slow blues, male vocal","lyrics":"[verse]\n...","stems":"vocal"}'minimax and acestep make one mixed track and refuse anything but mix. supports_stems in capabilities says which is which.
Progress
A job reports which phase it is in. Show the phase name; the fraction moves but its total can shrink.
| Phases | |
|---|---|
minimax | writing → solving → decoding |
acestep | solving → decoding |
yue | writing → refining → decoding |
Length
Time grows with length and steps. On an M-series laptop a ten-second clip takes a minute or two. Songs are capped at ten seconds by default; raise it in frames at 25 Hz:
DPPAN_MUSIC_MAX_FRAMES=1500 dppan-orchestrator # one minuteConfiguration
| Variable | Default | |
|---|---|---|
DPPAN_MUSIC_BUNDLE | unset | Model directories, comma-separated. Unset uses ~/.dppan/models/bundles |
DPPAN_MUSIC_MAX_FRAMES | 250 (10 s) | Longest song, in frames at 25 Hz |
DPPAN_MUSIC_STEPS | 0 (the model's own) | Default solver steps |
DPPAN_MUSIC_THREADS | 0 (the machine's) | CPU threads for music |
DPPAN_MUSIC_SYNC_TIMEOUT_SECS | 900 | How long /v1/audio/music waits before returning a job ID to poll |
Default steps by model:
| Model | Steps | |
|---|---|---|
minimax | 30 | Time grows with it |
acestep | 8 | Fixed; another count is refused |
yue | — | Has no step count |
Known limitations
minimax's defaultshiftandguidanceare estimates, as the publisher does not give them. If a song sounds wrong, both can be set per request.acestepwithout a reference clip has an arbitrary timbre.