Wan-2.2 Speech-to-Video 14B
Integra
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/it/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"
}
}
Chiama il modello Wan-2.2 Speech-to-Video 14B (wan/v2.2-14b/speech-to-video) tramite Doitong API. Documentazione per gli agenti: https://doitong.com/it/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"
}
Se lo stato della risposta è "queued" o "running", interroga GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 finché non diventa "succeeded"; i file si trovano in outputs[].url. POST https://api.doitong.ru/v1/quote/wan/v2.2-14b/speech-to-video con lo stesso body restituisce il prezzo esatto prima dell'esecuzione.
File come nell'esempio: 0,50 $ 500 crediti API · ≈ 53,79 ₽ i tuoi file vengono misurati prima dell'esecuzione Esegui in questa pagina
La tua nuova chiave API. Viene mostrata solo ora ed è già presente nel codice e nel campo della chiave API qui sotto. Mantienila segreta: non inserirla mai nel codice eseguito in un browser.
Creato su Doitong
Lavori pubblici creati con Wan v22 Large dalla community di Doitong. Riutilizza un prompt con un clic.
Video
Создай 30-секундный обучающий музыкальный ролик для детей 3–5 лет. Тема: транспорт. Яркая 2D-анимация, весёлый водитель в кепке, крупные машины, пастельные цвета. 0:00–0:10 приветствие под музыку; 0:10–0:30 песенка: "Машина едет би-би, би-би", "Поезд едет ту-ту, ту-ту". Бодрая детская музыка...
Video
Создай 30-секундный обучающий музыкальный ролик для детей 3–5 лет. Тема: транспорт. Яркая 2D-анимация, тот же весёлый водитель в кепке, самолёт. 0:00–0:15 песенка: "Самолёт летит вж-ж-ж, вж-ж-ж"; 0:15–0:25 интерактивная пауза: водитель спрашивает "Как гудит машина?", пауза; 0:25–0:30 финальный...
Crea una richiesta
I controlli vengono generati dallo schema del modello. Il codice e il prezzo si aggiornano mentre li modifichi.
/run/wan/v2.2-14b/speech-to-video?wait=20
preventivo → 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
}
}
}
Esegui questa richiesta
La tua chiave rimane in questo browser: viene inviata solo al Doitong API e salvata in localStorage solo se selezioni Ricorda. Ottieni una chiave API
Informazioni su Wan-2.2 Speech-to-Video 14B
Richiede un `prompt`, un `image_url` sorgente e un `audio_url`, quindi produce un video del soggetto raffigurato guidato dall'audio. `num_frames` va da 40 a 120 in multipli di 4, a 16 fps per impostazione predefinita. `resolution` può essere 480p, 580p o 720p. Sono regolabili i passi di campionamento, la guidance, l'interpolazione e un `negative_prompt`.
Parametri
Invia il nome canonico oppure il nome nativo, non entrambi. Nomi canonici
promptobbligatorio
negative_promptfacoltativo
num_framesfacoltativo
frames_per_secondfacoltativo
seedfacoltativo
resolutionfacoltativo
num_inference_stepsfacoltativo
enable_safety_checkerfacoltativo
enable_output_safety_checkerfacoltativo
guidance_scalefacoltativo
shiftfacoltativo
video_qualityfacoltativo
video_write_modefacoltativo
image_urlobbligatorio
image
audio_urlobbligatorio
audio
I parametri file accettano un URL pubblico https://, un URI data: fino a 10 MB oppure il file_url di un caricamento. File
Output
{
"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"
}
}
Campi dell'output
- video
- object {url, content_type, file_name, file_size}File video prodotto dalla generazione.
Altre varianti di Wan v22 Large
Altri modelli: Lipsync e avatar
Per gli agenti AI: questa pagina in Markdown è disponibile all'indirizzo https://doitong.com/it/developers/models/wan/v2.2-14b/speech-to-video.md. Tutti i modelli e le guide: https://doitong.com/developers/llms.txt