Njuolgga sisdollui

Wan-2.2 Speech-to-Video 14B

Integrere

Modealla-id wan/v2.2-14b/speech-to-video
# 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/wan/v2.2-14b/speech-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# 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"

Fiillat nugo ovdamearka: 0,50 $ 500 API-kreditta du fiillat mihtiduvvojit ovdal vuodjámis Vuodje dán siiddu alde

Oza API-čoavdaga
Alibaba Gubbelsynchroniseren ja avatárat Gubbelsynchroniserengitta 720p #audio-to-video#talking-head

Ráhkada hupmavideoa stahtalaš govvosis ja jietafiillas, teavstaprompta stivren

Ráhkaduvvon Doitongis

Doitong-bargosearvvi almmolaš barggut, ráhkaduvvon Wan v22 Large bokte. Geavat fas jearaldaga ovtta deaddilemiin.

Almmolaš barggut čájehuvvojit: 5
Create a highly realistic UGC-style smartphone video inside a modern commercial airplane during a... Video

Create a highly realistic UGC-style smartphone video inside a modern commercial airplane during a daytime flight. Natural cabin lighting, subtle handheld camera movement, authentic airplane ambience, realistic passengers and natural acting. The video must feel like a real spontaneous phone...

**SORA 2 PROMPT — 20 seconds, vertical 9:16** Create a highly realistic UGC-style smartphone vide... Video

**SORA 2 PROMPT — 20 seconds, vertical 9:16** Create a highly realistic UGC-style smartphone video inside a modern commercial airplane during a daytime flight. Natural cabin lighting, subtle handheld camera movement, authentic airplane ambience, realistic passengers and natural acting. The video...

Create a realistic cinematic 20-second video, filmed like a high-budget modern commercial with na... Video

Create a realistic cinematic 20-second video, filmed like a high-budget modern commercial with natural acting, realistic lighting and believable facial expressions. All dialogue is spoken naturally in French. **SCENE 1 — EXPENSIVE RESTAURANT, EVENING — 0–5 sec** A young man in his late 20s is...

Create a realistic cinematic UGC-style commercial video, exactly 30 seconds long. The entire scen... Video

Create a realistic cinematic UGC-style commercial video, exactly 30 seconds long. The entire scene takes place inside a modern passenger airplane during a daytime flight. Natural smartphone-like cinematography, realistic airplane cabin, authentic passengers, natural lighting, realistic skin...

TITLE: Santa's Secret Christmas Selfie with Dasha 🎄 VIDEO FORMAT: 15–20 seconds, vertical 9:16, c... Video

TITLE: Santa's Secret Christmas Selfie with Dasha 🎄 VIDEO FORMAT: 15–20 seconds, vertical 9:16, cinematic Christmas short film, high-quality realistic 3D animation. REFERENCE IMAGE — DASHA_001 Use the uploaded image as the exact character reference for Dasha. Preserve her recognizable face,...

Ráhkat jearaldaga

Kontrollat ráhkaduvvojit modealla skeama vuođul. Koda ja haddi ođasmahttojuvvojit go rievddadat daid.

•gáibiduvvo

Teakstabivdda geavahuvvon videoráhkadeapmái.

•gáibiduvvo image_url
Luoitte fiilla, dahje

Gáldogovva URL; válljejuvvon govvaráio mearrida dárbbašuvvo go ovdameannudeapmi: eahpeheivehus dagaha sturrodaddama ja dasto guovddáš-govvema.

•gáibiduvvo audio_url
Luoitte fiilla, dahje

URL jietnafiilii.

resolution standárda 480p

Boađusvideo resolušuvdna: 480p, 580p dahje 720p.

standárda 80

Vállje 4:in máŋgosa 40–120 gaskkas meroštallan dihte man olu rámmat ráhkaduvvojit.

Viiddiduvvon negative_prompt · video_quality · video_write_mode · frames_per_second · num_inference_steps · guidance_scale · shift · seed · enable_safety_checker · enable_output_safety_checker
standárda

Negatiiva bivdda mii geavahuvvo video ráhkadeamis.

video_quality standárda high

Boađusvideo kvalitehtaheivehus, mii lasihedje heivehusa vuogi mielde stuorát fiillaid buoret govvii.

video_write_mode standárda balanced

Videočájeheami dáhpi, mas balanced addá gávnnusvuođa jođánisvuođa ja kvalitehta gaskkas. Vállje small unnimus fiillaid ja guhkemuš čájeheami várás; jođáneabbo čájeheapmi máhcaha bohtosiid johtileappot muhto ráhkada stuorát fiillaid.

standárda 16

Ráhkaduvvon video rámmajohtalus, árvvut 4 gitta 60 rádjai; `adjust_fps_for_interpolation` false:i bidjá dán johtalusa rievdatkeahttá. Interpolášuvnna geavahettiin ja `adjust_fps_for_interpolation` true:in (dan standárdaárvu), máŋge dán johtalusa interpolerejuvvon rámmaid lohkui ovdal go oaččut loahpalaš FPS:a. Ovdamearka: 16 FPS ja 1 interpolerejuvvon rámma šaddá 32 FPS.

standárda 27

Sampling-láhtta lohku, mas guhkit barganáigi addá buoret kvalitehta.

standárda 3.5

Classifier-free guidance nanusvuohta, mas kvalitehtamáhca vejolašvuohta lonohallá lagabui bivdda čuovvuma go skála stuorru.

standárda 5

Video shift-heivehus, dárbbašlaš guhkkodat 1.0–10.0.

Sádji, mii dahká ráhkadeami reprodukšuvnnalažžan. None bidjan vállje sádji juhkosiid mielde.

POST /run/wan/v2.2-14b/speech-to-video?wait=20 haddemearrádus → 0,50 $
# 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/wan/v2.2-14b/speech-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# 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"

Geavat dán ohcamuša

Du key báhcá dán fierpmádatlogan: dat sáddejuvvo dušše Doitong API:ii ja vurkejuvvo (localStorage) dušše jos válljet Remember. Viečča API-keya

Dát lea Wan-2.2 Speech-to-Video 14B birra

Dárbbaša `prompt`-a, gáldu `image_url`-a ja `audio_url`-a, ja ráhkada videoa, mas govvosa fáhta lea jiena stivrejuvvon. `num_frames` lea 40 rájes 120 rádjái 4-multipluin, defaulta 16 fps. `resolution` sáhttá leat 480p, 580p dahje 720p. Sampling-lávddit, stivren, interpolášuvdna ja `negative_prompt` sáhttet heivehuvvot.

Parametterat

Sádde kanonala nama dahje iežas nama, ii goappašiid. Kanonala namat

NammaŠládja StandárdaDohkkehuvvon Govvádus
promptgáibiduvvo
Šládjastring
Teakstabivdda geavahuvvon videoráhkadeapmái.
negative_prompteaktodáhtolaš
Šládjastring
Standárda
Negatiiva bivdda mii geavahuvvo video ráhkadeamis.
num_frameseaktodáhtolaš
Šládjainteger
Standárda80
40 – 120
Vállje 4:in máŋgosa 40–120 gaskkas meroštallan dihte man olu rámmat ráhkaduvvojit.
frames_per_secondeaktodáhtolaš
Šládjainteger | null
Standárda16
4 – 60
Ráhkaduvvon video rámmajohtalus, árvvut 4 gitta 60 rádjai; `adjust_fps_for_interpolation` false:i bidjá dán johtalusa rievdatkeahttá. Interpolášuvnna geavahettiin ja `adjust_fps_for_interpolation` true:in (dan standárdaárvu), máŋge dán johtalusa interpolerejuvvon rámmaid lohkui ovdal go oaččut loahpalaš FPS:a. Ovdamearka: 16 FPS ja 1 interpolerejuvvon rámma šaddá 32 FPS.
seedeaktodáhtolaš
Šládjainteger | null
Sádji, mii dahká ráhkadeami reprodukšuvnnalažžan. None bidjan vállje sádji juhkosiid mielde.
resolutioneaktodáhtolaš
Šládjaenum
Standárda480p
480p580p720p
Boađusvideo resolušuvdna: 480p, 580p dahje 720p.
num_inference_stepseaktodáhtolaš
Šládjainteger
Standárda27
2 – 40
Sampling-láhtta lohku, mas guhkit barganáigi addá buoret kvalitehta.
enable_safety_checkereaktodáhtolaš
Šládjaboolean
Standárdafalse
Sisaaddi sihkkarvuođadárkkisteapmi ovdal gieđahallama, maid dušše autoriserejuvvon kontot sáhttet čájehit eret. Autorisašuvnna haga jearaldagat dárkkistuvvojit álo; muđui true aktiverii dárkkisteami.
enable_output_safety_checkereaktodáhtolaš
Šládjaboolean
Standárdafalse
Dárkkista ráhkaduvvon video sihkkarvuođa; true árvu aktiverii ráhkadeami maŋŋá dahkkojuvvon dárkkisteami.
guidance_scaleeaktodáhtolaš
Šládjanumber
Standárda3.5
1 – 10
Classifier-free guidance nanusvuohta, mas kvalitehtamáhca vejolašvuohta lonohallá lagabui bivdda čuovvuma go skála stuorru.
shifteaktodáhtolaš
Šládjanumber
Standárda5
1 – 10
Video shift-heivehus, dárbbašlaš guhkkodat 1.0–10.0.
video_qualityeaktodáhtolaš
Šládjaenum
Standárdahigh
lowmediumhighmaximum
Boađusvideo kvalitehtaheivehus, mii lasihedje heivehusa vuogi mielde stuorát fiillaid buoret govvii.
video_write_modeeaktodáhtolaš
Šládjaenum
Standárdabalanced
fastbalancedsmall
Videočájeheami dáhpi, mas balanced addá gávnnusvuođa jođánisvuođa ja kvalitehta gaskkas. Vállje small unnimus fiillaid ja guhkemuš čájeheami várás; jođáneabbo čájeheapmi máhcaha bohtosiid johtileappot muhto ráhkada stuorát fiillaid.
image_urlgáibiduvvo image
Šládjaurl · image
Gáldogovva URL; válljejuvvon govvaráio mearrida dárbbašuvvo go ovdameannudeapmi: eahpeheivehus dagaha sturrodaddama ja dasto guovddáš-govvema.
audio_urlgáibiduvvo audio
Šládjaurl · audio
URL jietnafiilii.
gáibiduvvo Kanonala namma, maid sáhttá geavahit

Fiilaparametterat váldet almmolaš https:// URL:a, data: URI:a gitta 10 MB, dahje uploada file_url:a. Fiillat

Boađus

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "wan/v2.2-14b/speech-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": 500,
    "usd": "0.50",
    "charged": 500,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_url": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Du fiillat, du válljenJuohke outputs[].url lea kopia min vurkemis: bisuhuvvo álo (mákso GB-mánu mielde) dahje 7 beaivvi nuvttá, du konto­o heiveheami dahje ?storage= mielde.
Seammá hápmi juohke modeallastype, url, content_type, width, height ja duration, govvii, videoii ja jienai seammá ládje. output lea modealla iežas boađusobjekta.
Outputa giettit
video
object {url, content_type, file_name, file_size}Ráhkadeami bokte buvttaduvvon videofiila.

Eanet modeallat: Gubbelsynchroniseren ja avatárat

AI-agenttaide: dán siidu Markdowna lea dáppe https://doitong.com/se/developers/models/wan/v2.2-14b/speech-to-video.md. Buot modeallat ja ráđit: https://doitong.com/developers/llms.txt