Wan-2.2 Speech-to-Video 14B

Integra

Id tal-mudell 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.ru/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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/wan/v2.2-14b/speech-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "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",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/wan/v2.2-14b/speech-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/mt/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.ru/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

# 2. Your agent calls the "run" tool with:
{
  "model_id": "wan/v2.2-14b/speech-to-video",
  "input": {
    "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"
  }
}

Ċempel il-mudell Wan-2.2 Speech-to-Video 14B (wan/v2.2-14b/speech-to-video) permezz tad-Doitong API. Dokumentazzjoni għall-aġenti: https://doitong.com/mt/developers/models/wan/v2.2-14b/speech-to-video.md

POST https://api.doitong.ru/v1/run/wan/v2.2-14b/speech-to-video?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "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"
}

Jekk l-istatus tar-rispons huwa "queued" jew "running", agħmel polling fuq GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 sakemm ikun "succeeded"; il-fajls jinsabu f’outputs[].url. POST https://api.doitong.ru/v1/quote/wan/v2.2-14b/speech-to-video bl-istess body jirritorna l-prezz eżatt qabel it-tħaddim.

Fajls bħall-eżempju: $0.50 500 krediti tal-API · ≈ ₽53.79 il-fajls tiegħek jitkejlu qabel it-tħaddim Ħaddmu f’din il-paġna

Ikseb ċavetta API

Alibaba Lipsync u avatars Lipsyncsa 720p #audio-to-video#talking-head

Joħloq vidjo jitkellem minn immaġni wieqfa u fajl awdjo, iggwidat minn prompt testwali

OpenAPI Markdown

Magħmul fuq Doitong

Xogħlijiet pubbliċi magħmula b’Wan v22 Large mill-komunità ta’ Doitong. Uża prompt mill-ġdid bi klikk waħda.

Xogħlijiet pubbliċi murija: 2

Prezz għal kull sekonda tal-vidjo tal-output tiegħek

Prezz ibbażat fuq l-input tiegħek

minn $0.10 / sekonda ta’ vidjo tal-output

100 krediti tal-API / sekonda ta’ vidjo tal-output · ≈ ₽10.76

Din it-talba: 5 sekondi × $0.10 (480p) $0.50 500 krediti tal-API · ≈ ₽53.79

Ħaddem · $0.50

Iċċarġjat biss jekk jirnexxi, u rimborżat awtomatikament jekk ifalli.

num_frames prestabbilit 80

resolution prestabbilit 480p

Prezz skont il-livell

480p	$0.10 / sekonda ta’ vidjo tal-output
580p	$0.15 / sekonda ta’ vidjo tal-output
720p	$0.20 / sekonda ta’ vidjo tal-output

It-titlu juri l-inqas livell; il-kwotazzjoni tikkalkula l-prezz tal-input eżatt tiegħek.

Il-fajls tiegħek jitkejlu qabel it-tħaddim (tul, riżoluzzjoni, rata tal-frejms); il-kwotazzjoni tirritorna l-prezz eżatt u t-tħaddim jiċċarġja eżattament dak.

Endpoint tal-kwotazzjoni: POST /quote/{id}

Ibni talba

Il-kontrolli jiġu ġġenerati mill-iskema tal-mudell. Il-kodiċi u l-prezz jaġġornaw hekk kif tibdilhom.

prompt •meħtieġ

Prompt testwali użat biex jiġi ġġenerat il-vidjo.

image •meħtieġ image_url

Waqqa’ fajl, jew

URL tal-immaġni tas-sors, bir-ratio tal-aspett magħżul jiddetermina jekk hemmx bżonn ta’ preprocessing: nuqqas ta’ qbil iqanqal ridimensjonar segwit minn crop ċentrali.

audio •meħtieġ audio_url

Waqqa’ fajl, jew

URL li tindika l-fajl awdjo.

resolution prestabbilit 480p

Riżoluzzjoni tal-vidjo output: 480p, 580p jew 720p.

num_frames prestabbilit 80

Agħżel multiplu ta’ 4 bejn 40 u 120 biex tissettja kemm jiġu ġġenerati frejms.

Avvanzat negative_prompt · video_quality · video_write_mode · frames_per_second · num_inference_steps · guidance_scale · shift · seed · enable_safety_checker · enable_output_safety_checker

negative_prompt prestabbilit

Prompt negattiv applikat waqt il-ġenerazzjoni ta’ vidjo.

video_quality prestabbilit high

Setting tal-kwalità tal-vidjo output li jiskambja fajls akbar għal viżwali mtejba hekk kif jiżdied is-setting.

video_write_mode prestabbilit balanced

Modalità tal-kitba tal-vidjo, b’balanced toffri kompromess bejn il-veloċità u l-kwalità. Agħżel small għall-iżgħar fajls u l-iktar kitba bil-mod; kitba aktar mgħaġġla tirritorna r-riżultati qabel iżda toħloq fajls akbar.

frames_per_second prestabbilit 16

Rata tal-frejms tal-vidjo ġġenerat, li taċċetta valuri minn 4 sa 60; l-issettjar ta’ `adjust_fps_for_interpolation` għal false iżomm din ir-rata kif inhi. Meta tintuża l-interpolazzjoni u `adjust_fps_for_interpolation` ikun true (il-valur prestabbilit tiegħu), immultiplika din ir-rata b’wieħed flimkien mal-għadd ta’ frejms interpolati biex tikseb l-FPS finali. Pereżempju, 16 FPS b’frejm interpolat wieħed isiru 32 FPS.

num_inference_steps prestabbilit 27

Għadd ta’ passi ta’ kampjunar; għadd ogħla jżid il-ħin tal-ipproċessar iżda jtejjeb il-kwalità.

guidance_scale prestabbilit 3.5

Qawwa tal-gwida mingħajr klassifikatur; skala ogħla tqarreb ir-riżultat lejn il-prompt iżda tista’ tnaqqas il-kwalità.

shift prestabbilit 5

Setting tal-bidla tal-vidjo, b’firxa permessa ta’ 1.0–10.0.

seed

Seed li jagħmel il-ġenerazzjoni riproduċibbli. L-issettjar tiegħu għal None jagħżel seed b’mod każwali.

POST /run/wan/v2.2-14b/speech-to-video?wait=20 kwotazzjoni → $0.50

# 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/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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/wan/v2.2-14b/speech-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "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",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/wan/v2.2-14b/speech-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "wan/v2.2-14b/speech-to-video",
      "input": {
        "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"
      },
      "wait_seconds": 20
    }
  }
}

Ħaddem din it-talba

Ċavetta API

Iċ-ċavetta tiegħek tibqa’ f’dan il-browser: tintbagħat biss lid-Doitong API u tiġi ssejvjata (localStorage) biss jekk timmarka Ftakar. Ftakar f’dan il-browser Ikseb ċavetta API

Dwar Wan-2.2 Speech-to-Video 14B

Jeħtieġ `prompt`, `image_url` tas-sors u `audio_url`, u jipproduċi vidjo tas-suġġett fir-ritratt immexxi mill-awdjo. `num_frames` ivarja minn 40 sa 120 f’multipli ta’ 4, b’16 fps prestabbiliti. `resolution` tista’ tkun 480p, 580p jew 720p. Il-passi tat-teħid tal-kampjuni, il-gwida, l-interpolazzjoni u `negative_prompt` jistgħu jiġu aġġustati.

Parametri

Ibgħat jew l-isem kanoniku jew l-isem nattiv, mhux it-tnejn. Ismijiet kanoniċi

IsemTip PrestabbilitPermess Deskrizzjoni

promptmeħtieġ

Tipstring

Prompt testwali użat biex jiġi ġġenerat il-vidjo.

negative_promptmhux obbligatorju

Tipstring

Prestabbilit

Prompt negattiv applikat waqt il-ġenerazzjoni ta’ vidjo.

num_framesmhux obbligatorju

Tipinteger

Prestabbilit80

40 – 120

Agħżel multiplu ta’ 4 bejn 40 u 120 biex tissettja kemm jiġu ġġenerati frejms.

frames_per_secondmhux obbligatorju

Tipinteger | null

Prestabbilit16

4 – 60

seedmhux obbligatorju

Tipinteger | null

Seed li jagħmel il-ġenerazzjoni riproduċibbli. L-issettjar tiegħu għal None jagħżel seed b’mod każwali.

resolutionmhux obbligatorju

Tipenum

Prestabbilit480p

480p580p720p

Riżoluzzjoni tal-vidjo output: 480p, 580p jew 720p.

num_inference_stepsmhux obbligatorju

Tipinteger

Prestabbilit27

2 – 40

Għadd ta’ passi ta’ kampjunar; għadd ogħla jżid il-ħin tal-ipproċessar iżda jtejjeb il-kwalità.

enable_safety_checkermhux obbligatorju

Tipboolean

Prestabbilitfalse

Verifika tas-sigurtà tal-input qabel l-ipproċessar, li kontijiet awtorizzati biss jistgħu jitfu. Talbiet mingħajr awtorizzazzjoni dejjem jiġu vverifikati; inkella, true jattiva l-verifika.

enable_output_safety_checkermhux obbligatorju

Tipboolean

Prestabbilitfalse

Jikkontrolla l-verifika tas-sigurtà tal-vidjo ġġenerat; true jattiva kontroll wara l-ġenerazzjoni.

guidance_scalemhux obbligatorju

Tipnumber

Prestabbilit3.5

1 – 10

Qawwa tal-gwida mingħajr klassifikatur; skala ogħla tqarreb ir-riżultat lejn il-prompt iżda tista’ tnaqqas il-kwalità.

shiftmhux obbligatorju

Tipnumber

Prestabbilit5

1 – 10

Setting tal-bidla tal-vidjo, b’firxa permessa ta’ 1.0–10.0.

video_qualitymhux obbligatorju

Tipenum

Prestabbilithigh

lowmediumhighmaximum

Setting tal-kwalità tal-vidjo output li jiskambja fajls akbar għal viżwali mtejba hekk kif jiżdied is-setting.

video_write_modemhux obbligatorju

Tipenum

Prestabbilitbalanced

fastbalancedsmall

image_urlmeħtieġ image

Tipurl · image

URL tal-immaġni tas-sors, bir-ratio tal-aspett magħżul jiddetermina jekk hemmx bżonn ta’ preprocessing: nuqqas ta’ qbil iqanqal ridimensjonar segwit minn crop ċentrali.

audio_urlmeħtieġ audio

Tipurl · audio

URL li tindika l-fajl awdjo.

meħtieġ Isem kanoniku, aċċettat ukoll

Il-parametri tal-fajls jaċċettaw URL pubbliku https://, URI data: sa 10 MB, jew file_url ta’ upload. Fajls

Output

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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}

Il-fajls tiegħek, l-għażla tiegħekKull outputs[].url huwa kopja fil-ħażna tagħna: miżmuma għal dejjem (imħallsa għal kull GB-xahar) jew 7 ijiem b’xejn, skont l-issettjar tal-kont tiegħek jew ?storage=.

L-istess struttura fuq kull mudelltype, url, content_type, width, height u duration, kemm għall-immaġnijiet kif ukoll għall-vidjo u l-awdjo. output huwa l-oġġett tar-riżultat tal-mudell innifsu.

Oqsma tal-output

video: object {url, content_type, file_name, file_size}Fajl vidjo prodott mill-ġenerazzjoni.

Aktar mudelli: Lipsync u avatars

Għall-aġenti tal-AI: din il-paġna bħala Markdown tinsab fuq https://doitong.com/mt/developers/models/wan/v2.2-14b/speech-to-video.md. Il-mudelli u l-gwidi kollha: https://doitong.com/developers/llms.txt

Magħmul fuq Doitong

Ibni talba

Ħaddem din it-talba

Dwar Wan-2.2 Speech-to-Video 14B

Parametri

Output

Varjanti oħra ta’ Wan v22 Large

Aktar mudelli: Lipsync u avatars