Saltar al cuntegna

MiniMax Music 3

Integrar

ID dal model minimax/music-3
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/minimax/music-3?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Warm indie folk, acoustic guitar and soft brushed drums, gentle female vocal, 92 BPM, nostalgic summer evening",
    "lyrics": "[verse]\nPorch lights humming on the edge of town\nWe count the fireflies as the sun goes down\n[chorus]\nStay a little longer, the night is young\nSing me the song that we never sung",
    "duration": 30
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Questa dumonda: $0,06 60 credits API Lantschar sin questa pagina

Obtegna ina clav API

Exempels

Output · ~84 s

PromptWarm indie folk, acoustic guitar and soft brushed drums, gentle female vocal, 92 BPM, nostalgic summer evening

30 s$0,06 · 60 credits API

Construir ina dumonda

Ils controls vegnan generads dal schema dal model. Il code e ​​il pretsch s'actualiseschan durant che ti als midas.

•obligatori

Prompt per la generaziun da musica che po utilisar ina Structured Caption per in control precis: cumbinescha l'arranschament e ils detagls vocals specifics da mintga secziun cun metadatas globalas che specifitgeschan genre, BPM, tonalitad e progressiun emoziunala. Ina descripziun generala cuvra il stil e l'umor giavischads, l'utilisaziun da vocals e instruments, sco er l'arranschament.

•obligatori

Text da la chanzun da chantà; tut ils pleds sin la medema lingia sco in tag da structura inizial vegnan eliminads tenor il contract d'input dal model. Tegna mintga tag sin ina lingia separada, inclusiv [intro], [verse], [pre-chorus], [chorus], [post-chorus], [bridge], [instrumental], [solo] e [outro].

Limita da la durada da l'audio, mesirada en secunda, e betg ina lunghezza garantida da l'output. La resposta rapporta la durada effectiva, che po esser pli curta sche la generaziun finescha baud.

Avanzà num_inference_steps · guidance_scale · seed
standard 30

Dumber da pass Euler per il flow matching entaifer mintga bloc da denoising da 8 secunda.

standard 1.7

Furza dal classifier-free guidance durant il flow matching.

Seed per ina generaziun reproducibla, tschernì casualmain sche ti na furneschas nagina valur.

POST /run/minimax/music-3?wait=20 calculaziun → $0,06
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/minimax/music-3?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Warm indie folk, acoustic guitar and soft brushed drums, gentle female vocal, 92 BPM, nostalgic summer evening",
    "lyrics": "[verse]\nPorch lights humming on the edge of town\nWe count the fireflies as the sun goes down\n[chorus]\nStay a little longer, the night is young\nSing me the song that we never sung",
    "duration": 30
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Executar questa dumonda

Tia clav resta en quest browser: ella vegn tramessa mo al Doitong API e memorisada (localStorage) mo sch'ella scheccas Tiar a memoria. Obtegnair ina clav API

Davart MiniMax Music 3

MiniMax Music 3 chanta tes lyrics sur in arranschament cumplet. Descriva genre, tempo, tonalitad, atmosfera, vuschs ed instruments en il prompt e marca la structura da la chanzun en ils lyrics cun tags sco [verse], [chorus] e [bridge], mintgin sin sia atgna lingia. La durada (1 fin 300 secundas, 60 per standard) è in limit superiur; la chanzun po finir pli baud.

Parameters

NumTip StandardPermess Descripziun
promptobligatori
Tipstring
Prompt per la generaziun da musica che po utilisar ina Structured Caption per in control precis: cumbinescha l'arranschament e ils detagls vocals specifics da mintga secziun cun metadatas globalas che specifitgeschan genre, BPM, tonalitad e progressiun emoziunala. Ina descripziun generala cuvra il stil e l'umor giavischads, l'utilisaziun da vocals e instruments, sco er l'arranschament.
lyricsobligatori
Tipstring
Text da la chanzun da chantà; tut ils pleds sin la medema lingia sco in tag da structura inizial vegnan eliminads tenor il contract d'input dal model. Tegna mintga tag sin ina lingia separada, inclusiv [intro], [verse], [pre-chorus], [chorus], [post-chorus], [bridge], [instrumental], [solo] e [outro].
durationopziunal
Tipnumber
Standard60
1 – 300
Limita da la durada da l'audio, mesirada en secunda, e betg ina lunghezza garantida da l'output. La resposta rapporta la durada effectiva, che po esser pli curta sche la generaziun finescha baud.
seedopziunal
Tipinteger | null
Seed per ina generaziun reproducibla, tschernì casualmain sche ti na furneschas nagina valur.
num_inference_stepsopziunal
Tipinteger
Standard30
1 – 100
Dumber da pass Euler per il flow matching entaifer mintga bloc da denoising da 8 secunda.
guidance_scaleopziunal
Tipnumber
Standard1.7
0 – 20
Furza dal classifier-free guidance durant il flow matching.
obligatori

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "minimax/music-3",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 60,
    "usd": "0.06",
    "charged": 60,
    "refunded": 0
  },
  "input": {
    "prompt": "Genre: acoustic pop. BPM: 96. Key: C major. Warm and intimate, soft female vocal, guitar and light piano",
    "lyrics": "[verse]\nMorning light filtering through the pine\nEvery quiet street is yours and mine\n[chorus]\nSoftly the world begins to breathe",
    "duration": 30
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    },
    "seed": 42,
    "duration": 5
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Tias datotecas, tia decisiunMintga outputs[].url è ina copia en nossa memorisaziun: conservada per adina (pajà per GB-mes) u 7 dis gratuitamain, tenor la configuraziun dal conto u ?storage=.
La medema structura per mintga modeltype, url, content_type, width, height e duration, tant per maletgs sco per video e audio. output è l'object da resultat dal model sez.
Champs da l'output
audio
object {url, content_type, file_name, file_size}Datoteca audio d'output en format WAV stereo, cun 44.1 kHz e samples da 16-bit.
seed
integerSeed casual utilisà durant la generaziun.
duration
numberRapporta quantas secunda audio èn vegnidas generadas effectivamain; quai na correspunda betg necessariamain a la durada dumandada.

Dapli models: Text a musica

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/minimax/music-3.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt