Wan-2.2 Speech-to-Video 14B

Integrar

ID dal model 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/rm/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"
  }
}

Cloma il model Wan-2.2 Speech-to-Video 14B (wan/v2.2-14b/speech-to-video) tras la Doitong API. Documentaziun per agents: https://doitong.com/rm/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"
}

Sche il status da la resposta è "queued" u "running", fa polling GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 fin ch'el è "succeeded"; las datotecas èn en outputs[].url. POST https://api.doitong.ru/v1/quote/wan/v2.2-14b/speech-to-video cun il medem body returna il pretsch exact avant l'execuziun.

Datotecas sco l'exempel: $0,50 500 credits API · ≈ ₽53,79 tias datotecas vegnan mesiradas avant l'execuziun Lantschar sin questa pagina

Obtegna ina clav API

Alibaba Lipsync e avatars Lipsyncfin a 720p #audio-to-video#talking-head

Crea in video discurrint a partir d'in maletg fix e d'in dat audio, guidà d'in prompt da text

OpenAPI Markdown

Fatg sin Doitong

Ovras publicas fatgas cun Wan v22 Large da la communitad Doitong. Reutilisescha in prompt cun in clic.

Ovras publicas mussadas: 3

Pretsch per secunda dal video d'output

Pretsch tenor vossa entrada

a partir da $0,10 / secunda da video d'output

100 credits API / secunda da video d'output · ≈ ₽10,76

Questa dumonda: 5 secundas × $0,10 (480p) $0,50 500 credits API · ≈ ₽53,79

Executar · $0,50

Facturà mo en cas da success, rembursà automaticamain en cas d'ina errur.

num_frames standard 80

resolution standard 480p

Pretsch tenor stgalim

480p	$0,10 / secunda da video d'output
580p	$0,15 / secunda da video d'output
720p	$0,20 / secunda da video d'output

Il titel mussa il stgalim il pli bass; la calculaziun fixescha il pretsch per tes input exact.

Voss datotecas vegnan mesiradas avant l'execuziun (durada, resoluziun, frequenza da maletgs); la calculaziun restituescha il pretsch exact e l'execuziun vegn addebitada exactamain tenor quel.

Endpoint da calculaziun: POST /quote/{id}

Construir ina dumonda

Ils controls vegnan generads dal schema dal model. Il code e il pretsch s'actualiseschan durant che ti als midas.

prompt •obligatori

Prompt da text utilisà per generar il video.

image •obligatori image_url

Trametta in datoteca u

URL dal maletg da funtauna; la relaziun d'aspect tschernida determinescha sche in pre-processament è necessari: ina divergenza chaschuna in redimensiunament suandà d'in tagl central.

audio •obligatori audio_url

Trametta in datoteca u

URL che mussa a la datoteca audio.

resolution standard 480p

Resoluziun dal video d'output: 480p, 580p u 720p.

num_frames standard 80

Tscherner in multipel da 4 tranter 40–120 per definir quants frames vegnan generads.

Avanzà 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 standard

Prompt negativ applitgà durant la generaziun d'in video.

video_quality standard high

Configuraziun da la qualitad dal video d'output, che baratta datotecas pli grondas per visuals meglers cura che la valur crescha.

video_write_mode standard balanced

Modus da scriver video, cun balanced sco cumpromiss tranter sveltezza e qualitad. Tscherner small per las datotecas las pli pitschnas e la scrittira la pli plauna; ina scrittira pli svelta returna ils resultats pli baud, ma creescha datotecas pli grondas.

frames_per_second standard 16

Frequentaziun da frames dal video generà, cun valurs da 4 fin 60; definir `adjust_fps_for_interpolation` a false mantegna questa frequentaziun senza midada. Cun interpolaziun activa e `adjust_fps_for_interpolation` true (ses standard), multiplitgar questa frequentaziun per in plus il dumber da frames interpolads per obtegnair la FPS finala. Per exempel, 16 FPS cun 1 frame interpolà daventan 32 FPS.

num_inference_steps standard 27

Dumber da pass da sampling, barattà temp d'elavuraziun pli lung per meglra qualitad cun l'augment dal dumber.

guidance_scale standard 3.5

Furza da la guida senza classifitgat, barattà ina pussaivla perdita da qualitad per ina concordanza pli stretga cun il prompt a mesira che la scala crescha.

shift standard 5

Configuraziun dal shift dal video, cun in interval permess da 1.0–10.0.

seed

Seed che renda la generaziun reproducibla. Cun definir None vegn tschernì in seed casualmain.

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

Executar questa dumonda

Clav API

Tia clav resta en quest browser: ella vegn tramessa mo al Doitong API e memorisada (localStorage) mo sch'ella scheccas Tiar a memoria. Memorisar en quest navigatur Obtegnair ina clav API

Davart Wan-2.2 Speech-to-Video 14B

Dovra in `prompt`, in `image_url` d'origin ed in `audio_url`, e producescha in video dal tema mussà manà da l'audio. `num_frames` tanscha da 40 fin 120 en multipels da 4, a 16 fps per standard. `resolution` po esser 480p, 580p u 720p. Pass da sampling, guidance, interpolaziun ed in `negative_prompt` pon vegnir adattads.

Parameters

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

NumTip StandardPermess Descripziun

promptobligatori

Tipstring

Prompt da text utilisà per generar il video.

negative_promptopziunal

Tipstring

Standard

Prompt negativ applitgà durant la generaziun d'in video.

num_framesopziunal

Tipinteger

Standard80

40 – 120

Tscherner in multipel da 4 tranter 40–120 per definir quants frames vegnan generads.

frames_per_secondopziunal

Tipinteger | null

Standard16

4 – 60

seedopziunal

Tipinteger | null

Seed che renda la generaziun reproducibla. Cun definir None vegn tschernì in seed casualmain.

resolutionopziunal

Tipenum

Standard480p

480p580p720p

Resoluziun dal video d'output: 480p, 580p u 720p.

num_inference_stepsopziunal

Tipinteger

Standard27

2 – 40

Dumber da pass da sampling, barattà temp d'elavuraziun pli lung per meglra qualitad cun l'augment dal dumber.

enable_safety_checkeropziunal

Tipboolean

Standardfalse

Controlla da segirezza da l'input avant l'elavuraziun, che mo contos autorisads pon deactivar. Dumondas senza autorisaziun vegnan adina controlladas; uschiglio activa true la controlla.

enable_output_safety_checkeropziunal

Tipboolean

Standardfalse

Controlla la segirezza dal video generà; true activa ina controlla suenter la generaziun.

guidance_scaleopziunal

Tipnumber

Standard3.5

1 – 10

Furza da la guida senza classifitgat, barattà ina pussaivla perdita da qualitad per ina concordanza pli stretga cun il prompt a mesira che la scala crescha.

shiftopziunal

Tipnumber

Standard5

1 – 10

Configuraziun dal shift dal video, cun in interval permess da 1.0–10.0.

video_qualityopziunal

Tipenum

Standardhigh

lowmediumhighmaximum

Configuraziun da la qualitad dal video d'output, che baratta datotecas pli grondas per visuals meglers cura che la valur crescha.

video_write_modeopziunal

Tipenum

Standardbalanced

fastbalancedsmall

image_urlobligatori image

Tipurl · image

URL dal maletg da funtauna; la relaziun d'aspect tschernida determinescha sche in pre-processament è necessari: ina divergenza chaschuna in redimensiunament suandà d'in tagl central.

audio_urlobligatori audio

Tipurl · audio

URL che mussa a la datoteca audio.

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": "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"
  }
}

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}Datoteca video producida da la generaziun.

Dapli models: Lipsync e avatars

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/wan/v2.2-14b/speech-to-video.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt

Fatg sin Doitong

Construir ina dumonda

Executar questa dumonda

Davart Wan-2.2 Speech-to-Video 14B

Parameters

Output

Autras variantes Wan v22 Large

Dapli models: Lipsync e avatars