Saltar al cuntegna

MMAudio V2

Integrar

ID dal model mmaudio-v2
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/mmaudio-v2?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/dev-api/2026/10/21/req_qicb9wfr7rqfo46hqcxollq6/0-QQGxyL6x8ywkCEWdZ94UY_YyJVjs3R.mp4",
    "prompt": "Gentle waves lapping against a wooden boat, oars creaking, seagulls calling in the distance, light wind",
    "duration": 5
  }'

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

Questa dumonda: $0,005 5 credits API · ≈ ₽0,53 Lantschar sin questa pagina

Obtegna ina clav API
Sony AI Audio 1–30 s #sound-effects#foley#video-to-audio

Agiunta effects da tun e atmosfera sincronisads ad in video senza tun a partir d'ina curta descripziun da text.

Exempels

Input
Output · ~20 s

PromptGentle waves lapping against a wooden boat, oars creaking, seagulls calling in the distance, light wind

5 s$0,005 · 5 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 che descriva l’audio da crear.

•obligatori video_url
Trametta in datoteca u

URL dal video utilisà sco funtauna per la generaziun audio.

Lunghezza da l’audio generà.

Avanzà negative_prompt · num_steps · cfg_strength · seed · mask_away_clip
standard

Prompt negativ che definescha quai che duai vegnir exclus durant la generaziun audio.

standard 25

Dumber da pass utilisads per la generaziun audio.

standard 4.5

Intensitad da Classifier Free Guidance.

Valur dal seed utilisà dal generatur da nums casuels.

POST /run/mmaudio-v2?wait=20 calculaziun → $0,005
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/mmaudio-v2?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/dev-api/2026/10/21/req_qicb9wfr7rqfo46hqcxollq6/0-QQGxyL6x8ywkCEWdZ94UY_YyJVjs3R.mp4",
    "prompt": "Gentle waves lapping against a wooden boat, oars creaking, seagulls calling in the distance, light wind",
    "duration": 5
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/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 MMAudio V2

MMAudio V2 guarda il video e generescha audio adattà: pass sincronisads, sprizzs, motors, fulla e atmosfera da stanza, dirigì da tes prompt e d'in prompt negativ opziunal. Generescha 1 fin a 30 secundas d'audio e retorna il video cun la nova banda sonora.

Parameters

Invia u il num canonic u il num nativ, betg omaduas. Nums canonics

NumTip StandardPermess Descripziun
video_urlobligatori video
Tipurl · video
URL dal video utilisà sco funtauna per la generaziun audio.
promptobligatori
Tipstring
Prompt che descriva l’audio da crear.
negative_promptopziunal
Tipstring
Standard
Prompt negativ che definescha quai che duai vegnir exclus durant la generaziun audio.
seedopziunal
Tipinteger | null
0 – 65 535
Valur dal seed utilisà dal generatur da nums casuels.
num_stepsopziunal
Tipinteger
Standard25
4 – 50
Dumber da pass utilisads per la generaziun audio.
durationopziunal
Tipnumber
Standard8
1 – 30
Lunghezza da l’audio generà.
cfg_strengthopziunal
Tipnumber
Standard4.5
0 – 20
Intensitad da Classifier Free Guidance.
mask_away_clipopziunal
Tipboolean
Standardfalse
Controlla sche il clip vegn mascrà ora.
obligatori Num canonic, er acceptà

Ils parameters da datotecas acceptan ina URL publica https://, ina URI data: fin a 10 MB u il file_url d'ina chargiada. Datotecas

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "mmaudio-v2",
  "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": 5,
    "usd": "0.005",
    "charged": 5,
    "refunded": 0
  },
  "input": {
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "prompt": "Night forest ambience, soft paws running on grass, crickets, gentle magical chimes",
    "duration": 6
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/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
video
object {url, content_type, file_name, file_size}Video d'output cun moviments dals lefs sincronisads.

Dapli models: Audio

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/mmaudio-v2.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt