Ruka hadi kwenye maudhui

MMAudio V2

Unganisha

Kitambulisho cha modeli 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"

Ombi hili: $ 0.005 salio za API 5 · ≈ ₽ 0.53 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
Sony AI Sauti 1–30 s #sound-effects#foley#video-to-audio

Huongeza athari za sauti na mandhari zilizosawazishwa kwenye video kimya kutoka kwa maelezo mafupi ya maandishi.

Mifano

Ingizo
Tokeo · ~20 s

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

5 s$ 0.005 · salio za API 5

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

•inahitajika

Kidokezo kinachoeleza sauti ya kuunda.

•inahitajika video_url
Dondosha faili, au

URL ya video iliyotumika kama chanzo cha uzalishaji wa sauti.

Urefu wa sauti iliyozalishwa.

Ya kina negative_prompt · num_steps · cfg_strength · seed · mask_away_clip
chaguomsingi

Kidokezo hasi kinachobainisha kitakachoondolewa wakati wa uzalishaji wa sauti.

chaguomsingi 25

Idadi ya hatua zinazotumika kwa uzalishaji wa sauti.

chaguomsingi 4.5

Nguvu ya Classifier Free Guidance.

Thamani ya seed inayotumiwa na jenereta ya nambari nasibu.

POST /run/mmaudio-v2?wait=20 makadirio → $ 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"

Endesha ombi hili

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Pata ufunguo wa API

Kuhusu MMAudio V2

MMAudio V2 hutazama video na kuzalisha sauti inayoendana nayo: hatua kwa mdundo, minyunyizo, injini, umati na mazingira ya chumba, ikiongozwa na kidokezo chako na kidokezo hasi cha hiari. Huzalisha sekunde 1 hadi 30 za sauti na hurudisha video yenye soundtrack mpya.

Vigezo

Tuma jina rasmi au jina asilia, si yote mawili. Majina rasmi

JinaAina ChaguomsingiInaruhusiwa Maelezo
video_urlinahitajika video
Ainaurl · video
URL ya video iliyotumika kama chanzo cha uzalishaji wa sauti.
promptinahitajika
Ainastring
Kidokezo kinachoeleza sauti ya kuunda.
negative_promptsi lazima
Ainastring
Chaguomsingi
Kidokezo hasi kinachobainisha kitakachoondolewa wakati wa uzalishaji wa sauti.
seedsi lazima
Ainainteger | null
0 – 65,535
Thamani ya seed inayotumiwa na jenereta ya nambari nasibu.
num_stepssi lazima
Ainainteger
Chaguomsingi25
4 – 50
Idadi ya hatua zinazotumika kwa uzalishaji wa sauti.
durationsi lazima
Ainanumber
Chaguomsingi8
1 – 30
Urefu wa sauti iliyozalishwa.
cfg_strengthsi lazima
Ainanumber
Chaguomsingi4.5
0 – 20
Nguvu ya Classifier Free Guidance.
mask_away_clipsi lazima
Ainaboolean
Chaguomsingifalse
Hudhibiti ikiwa klipu itafichwa kwa maski.
inahitajika Jina rasmi, pia linakubalika

Vigezo vya faili vinakubali URL ya umma ya https://, data: URI ya hadi 10 MB, au file_url ya upakiaji. Faili

Tokeo

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"
  }
}
Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.
Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.
Sehemu za tokeo
video
object {url, content_type, file_name, file_size}Video ya tokeo iliyo na miondoko ya midomo iliyosawazishwa.

Miundo zaidi: Sauti

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/mmaudio-v2.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt