Saltar al cuntegna

Kling 3.0 Pro Text to Video

Integrar

ID dal model kling-video/v3/pro/text-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/kling-video/v3/pro/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A paper boat drifts down a rain-filled street gutter at dusk. The camera follows at water level as raindrops ripple around it and neon reflections shimmer on the wet asphalt, then the boat tips over a small cascade into a puddle. Realistic water physics, shallow depth of field, cinematic.",
    "duration": 5,
    "generate_audio": false,
    "aspect_ratio": "16:9"
  }'

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

Questa dumonda: $0,56 560 credits API Lantschar sin questa pagina

Obtegna ina clav API
Kling Text a video Audio nativ3–15 s #cinematic#multi-shot

Clips cinematografics da 3 fin a 15 secundas d'in prompt, cun tun nativ e narraziun multi-shot.

Exempels

Output · ~141 s

PromptA paper boat drifts down a rain-filled street gutter at dusk. The camera follows at water level as raindrops ripple around it and neon reflections shimmer on the wet asphalt, then the boat tips over a small cascade into a puddle. Realistic water physics, shallow depth of field, cinematic.

5 sgenerate_audio: false16:9$0,56 · 560 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.

289 / 2500

Instrucziuns da text utilisadas per generar il video. Furnescha exactamain in da prompt u multi_prompt.

duration 5 s

Durada dal video d’output, mesirada en secundas.

aspect_ratio

Proporziun da la ladezza envers l’autezza dals frames en il video d’output.

Avanzà negative_prompt · shot_type · cfg_scale · multi_prompt
0 / 2500
shot_type standard customize

Tscherna co la generaziun da plirs plans planisescha ses plans; la selecziun da 'intelligent' deleghescha la structura dals plans al model.

standard 0.5

Definescha quant exactamain la generaziun suonda tes prompt cun CFG, l’abreviaziun per Classifier Free Guidance.

Prompts e duradas per singuls plans che, sche furnids, remplazzan il prompt singul per crear in video dividì en plirs plans.

POST /run/kling-video/v3/pro/text-to-video?wait=20 calculaziun → $0,56
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/kling-video/v3/pro/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A paper boat drifts down a rain-filled street gutter at dusk. The camera follows at water level as raindrops ripple around it and neon reflections shimmer on the wet asphalt, then the boat tips over a small cascade into a puddle. Realistic water physics, shallow depth of field, cinematic.",
    "duration": 5,
    "generate_audio": false,
    "aspect_ratio": "16:9"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/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 Kling 3.0 Pro Text to Video

Il model text-to-video da punta da Kling producescha moviment guliv e fisicamain plausibel sco er glisch en stil da film, e generescha per standard tun e discurrida adattads. Parta in clip en plirs shots cun prompts per shot, u lascha il model planisar sez ils cuts. 16:9, 9:16 u 1:1, mintga lunghezza da 3 fin 15 secundas, cun in prompt negativ e ina scala da guidance.

Parameters

NumTip StandardPermess Descripziun
promptopziunal
Tipstring | null
≤ 2 500 caracters
Instrucziuns da text utilisadas per generar il video. Furnescha exactamain in da prompt u multi_prompt.
durationopziunal
Tipenum
Standard5
3456789101112131415
Durada dal video d’output, mesirada en secundas.
multi_promptopziunal
Tipobject[]
Prompts e duradas per singuls plans che, sche furnids, remplazzan il prompt singul per crear in video dividì en plirs plans.
multi_prompt[].promptobligatori
Tipstring
Instrucziuns da text per il plan actual.
multi_prompt[].durationopziunal
Tipenum
Standard5
123456789101112131415
Durada dal plan actual, mesirada en secundas.
generate_audioopziunal
Tipboolean
Standardtrue
Activaziun da la generaziun d’audio video nativ, che sustegna vuschs en chinais u englais e translatescha automaticamain mintga autra lingua en englais. Per pled englais, scriva abreviaziuns e nums propris en maiusclas e tut il rest en minusclas.
shot_typeopziunal
Tipenum
Standardcustomize
customizeintelligent
Tscherna co la generaziun da plirs plans planisescha ses plans; la selecziun da 'intelligent' deleghescha la structura dals plans al model.
aspect_ratioopziunal
Tipenum
Standard16:9
16:99:161:1
Proporziun da la ladezza envers l’autezza dals frames en il video d’output.
negative_promptopziunal
Tipstring
Standardblur, distort, and low quality
≤ 2 500 caracters
cfg_scaleopziunal
Tipnumber
Standard0.5
0 – 1
Definescha quant exactamain la generaziun suonda tes prompt cun CFG, l’abreviaziun per Classifier Free Guidance.
obligatori

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "kling-video/v3/pro/text-to-video",
  "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": 560,
    "usd": "0.56",
    "charged": 560,
    "refunded": 0
  },
  "input": {
    "prompt": "Close-up of fireflies dancing in a dark forest at twilight, soft glowing particles, slow dolly forward",
    "duration": 5,
    "aspect_ratio": "16:9"
  },
  "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://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://vit.doitong.com/api/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 producì dal model.

Dapli models: Text a video

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/kling-video/v3/pro/text-to-video.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt