Wan-2.2 Speech-to-Video 14B

Unganisha

Kitambulisho cha modeli 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/sw/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"
  }
}

Piga modeli ya Wan-2.2 Speech-to-Video 14B (wan/v2.2-14b/speech-to-video) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/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"
}

Ikiwa hali ya jibu ni "queued" au "running", piga GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 mara kwa mara hadi iwe "succeeded"; faili ziko kwenye outputs[].url. POST https://api.doitong.ru/v1/quote/wan/v2.2-14b/speech-to-video yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Faili kama mfano: $ 0.50 salio za API 500 · ≈ ₽ 53.66 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

Alibaba Usawazishaji wa Midomo na Avatari Usawazishaji wa midomohadi 720p #audio-to-video#talking-head

Hutengeneza video ya mtu anayezungumza kutoka kwa picha tuli na faili la sauti, kwa kuongozwa na kidokezo cha maandishi

OpenAPI Markdown

Imetengenezwa kwenye Doitong

Kazi za umma zilizotengenezwa kwa Wan v22 Large na jumuiya ya Doitong. Tumia tena kidokezo kwa kubofya mara moja.

Kazi za umma zilizoonyeshwa: 3

Bei kwa kila sekunde ya video yako ya kutolewa

Bei kulingana na uingizaji wako

kuanzia $ 0.10 / sekunde ya video ya tokeo

salio za API 100 / sekunde ya video ya tokeo · ≈ ₽ 10.73

Ombi hili: sekunde 5 × $ 0.10 (480p) $ 0.50 salio za API 500 · ≈ ₽ 53.66

Endesha · $ 0.50

Hutozwa tu ikifanikiwa, na kurejeshewa kiotomatiki ikishindwa.

num_frames chaguomsingi 80

resolution chaguomsingi 480p

Bei kulingana na daraja

480p	$ 0.10 / sekunde ya video ya tokeo
580p	$ 0.15 / sekunde ya video ya tokeo
720p	$ 0.20 / sekunde ya video ya tokeo

Kichwa kinaonyesha daraja la chini zaidi; nukuu huweka bei ya ingizo lako halisi.

Faili zako hupimwa kabla ya kuendeshwa (urefu, mwonekano, kasi ya fremu); makadirio hurejesha bei kamili na uendeshaji hutozwa kiasi hicho hicho.

Endpoint ya makadirio: POST /quote/{id}

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

prompt •inahitajika

Kidokezo cha maandishi kilichotumika kuzalisha video.

image •inahitajika image_url

Dondosha faili, au

URL ya picha chanzo, huku uwiano wa pande uliochaguliwa ukiamua ikiwa uchakataji wa awali unahitajika: kutolingana husababisha kubadilisha ukubwa kisha kukata katikati.

audio •inahitajika audio_url

Dondosha faili, au

URL inayoelekeza kwenye faili ya sauti.

resolution chaguomsingi 480p

Mwonekano wa video ya tokeo: 480p, 580p au 720p.

num_frames chaguomsingi 80

Chagua kizidisho cha 4 ndani ya 40–120 ili kuweka idadi ya fremu zitakazozalishwa.

Ya kina 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 chaguomsingi

Kidokezo hasi kinachotumika wakati wa kutengeneza video.

video_quality chaguomsingi high

Mpangilio wa ubora wa video ya tokeo unaobadilisha ukubwa wa faili kwa picha bora zaidi kadiri thamani inavyoongezeka.

video_write_mode chaguomsingi balanced

Hali ya kuandika video, ambapo balanced hutoa uwiano kati ya kasi na ubora. Chagua small kwa faili ndogo zaidi na uandishi wa polepole zaidi; uandishi wa haraka hurudisha matokeo mapema lakini huunda faili kubwa zaidi.

frames_per_second chaguomsingi 16

Kasi ya fremu za video iliyozalishwa, inayokubali thamani kutoka 4 hadi 60; kuweka `adjust_fps_for_interpolation` kuwa false huhifadhi kasi hii bila mabadiliko. Interpolation inapotumika na `adjust_fps_for_interpolation` ikiwa true (chaguo lake chaguomsingi), zidisha kasi hii kwa moja pamoja na idadi ya fremu zilizointerpolatiwa ili kupata FPS ya mwisho. Kwa mfano, 16 FPS yenye fremu 1 iliyointerpolatiwa huwa 32 FPS.

num_inference_steps chaguomsingi 27

Idadi ya hatua za sampuli, ambapo muda mrefu wa uchakataji huleta ubora bora kadiri idadi inavyoongezeka.

guidance_scale chaguomsingi 3.5

Nguvu ya mwongozo isiyotegemea kiainishaji, ambapo ongezeko la kipimo hubadilisha uwezekano wa kupoteza ubora kwa ulinganifu wa karibu zaidi na kidokezo.

shift chaguomsingi 5

Mpangilio wa mgeuzo wa video, wenye masafa yanayoruhusiwa ya 1.0–10.0.

seed

Seed inayofanya uzalishaji uweze kurudiwa. Kuiweka kuwa None huchagua seed bila mpangilio.

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

Endesha ombi hili

Ufunguo wa API

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Kumbuka katika kivinjari hiki Pata ufunguo wa API

Kuhusu Wan-2.2 Speech-to-Video 14B

Inahitaji `prompt`, `image_url` ya chanzo na `audio_url`, kisha huzalisha video ya mhusika aliye kwenye picha inayoendeshwa na sauti. `num_frames` huanzia 40 hadi 120 kwa vizidishi vya 4, kwa 16 fps kwa chaguomsingi. `resolution` inaweza kuwa 480p, 580p au 720p. Hatua za usampulishaji, mwongozo, interpolation na `negative_prompt` zinaweza kurekebishwa.

Vigezo

Tuma jina rasmi au jina asilia, si yote mawili. Majina rasmi

JinaAina ChaguomsingiInaruhusiwa Maelezo

promptinahitajika

Ainastring

Kidokezo cha maandishi kilichotumika kuzalisha video.

negative_promptsi lazima

Ainastring

Chaguomsingi

Kidokezo hasi kinachotumika wakati wa kutengeneza video.

num_framessi lazima

Ainainteger

Chaguomsingi80

40 – 120

Chagua kizidisho cha 4 ndani ya 40–120 ili kuweka idadi ya fremu zitakazozalishwa.

frames_per_secondsi lazima

Ainainteger | null

Chaguomsingi16

4 – 60

seedsi lazima

Ainainteger | null

Seed inayofanya uzalishaji uweze kurudiwa. Kuiweka kuwa None huchagua seed bila mpangilio.

resolutionsi lazima

Ainaenum

Chaguomsingi480p

480p580p720p

Mwonekano wa video ya tokeo: 480p, 580p au 720p.

num_inference_stepssi lazima

Ainainteger

Chaguomsingi27

2 – 40

Idadi ya hatua za sampuli, ambapo muda mrefu wa uchakataji huleta ubora bora kadiri idadi inavyoongezeka.

enable_safety_checkersi lazima

Ainaboolean

Chaguomsingifalse

Ukaguzi wa usalama wa ingizo kabla ya uchakataji, ambao ni akaunti zilizoidhinishwa pekee zinazoweza kuuzima. Maombi yasiyo na idhini hukaguliwa kila mara; vinginevyo, true huwezesha ukaguzi.

enable_output_safety_checkersi lazima

Ainaboolean

Chaguomsingifalse

Hudhibiti ukaguzi wa usalama wa video iliyozalishwa; kuweka true huwezesha ukaguzi baada ya uzalishaji.

guidance_scalesi lazima

Ainanumber

Chaguomsingi3.5

1 – 10

Nguvu ya mwongozo isiyotegemea kiainishaji, ambapo ongezeko la kipimo hubadilisha uwezekano wa kupoteza ubora kwa ulinganifu wa karibu zaidi na kidokezo.

shiftsi lazima

Ainanumber

Chaguomsingi5

1 – 10

Mpangilio wa mgeuzo wa video, wenye masafa yanayoruhusiwa ya 1.0–10.0.

video_qualitysi lazima

Ainaenum

Chaguomsingihigh

lowmediumhighmaximum

Mpangilio wa ubora wa video ya tokeo unaobadilisha ukubwa wa faili kwa picha bora zaidi kadiri thamani inavyoongezeka.

video_write_modesi lazima

Ainaenum

Chaguomsingibalanced

fastbalancedsmall

image_urlinahitajika image

Ainaurl · image

URL ya picha chanzo, huku uwiano wa pande uliochaguliwa ukiamua ikiwa uchakataji wa awali unahitajika: kutolingana husababisha kubadilisha ukubwa kisha kukata katikati.

audio_urlinahitajika audio

Ainaurl · audio

URL inayoelekeza kwenye faili ya sauti.

inahitajika Jina rasmi, pia linakubalika

Vigezo vya faili vinakubali URL ya umma ya https://, data: URI ya hadi 10 MB, au file_url ya upakiaji. Faili

Tokeo

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"
  }
}

Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.

Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.

Sehemu za tokeo

video: object {url, content_type, file_name, file_size}Faili ya video iliyozalishwa.

Miundo zaidi: Usawazishaji wa Midomo na Avatari

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/wan/v2.2-14b/speech-to-video.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt

Imetengenezwa kwenye Doitong

Unda ombi

Endesha ombi hili

Kuhusu Wan-2.2 Speech-to-Video 14B

Vigezo

Tokeo

Tofauti nyingine za Wan v22 Large

Miundo zaidi: Usawazishaji wa Midomo na Avatari