AI Avatar Multi

Integra

Id tal-mudell ai-avatar/multi

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

# 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/ai-avatar/multi?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "first_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
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 = {
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "first_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ai-avatar/multi", 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": "ai-avatar/multi",
  "input": {
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "first_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }
}

Ċempel il-mudell AI Avatar Multi (ai-avatar/multi) permezz tad-Doitong API. Dokumentazzjoni għall-aġenti: https://doitong.com/mt/developers/models/ai-avatar/multi.md

POST https://api.doitong.ru/v1/run/ai-avatar/multi?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
  "first_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}

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/ai-avatar/multi bl-istess body jirritorna l-prezz eżatt qabel it-tħaddim.

Fajls bħall-eżempju: $1.81 1,810 krediti tal-API · ≈ ₽190.89 il-fajls tiegħek jitkejlu qabel it-tħaddim Ħaddmu f’din il-paġna

Ikseb ċavetta API

Open model Lipsync u avatars Lipsyncsa 720p #stylized#transform

Janima immaġni fissa f’vidjo ta’ konversazzjoni bejn żewġ persuni, immexxi minn track awdjo wieħed jew tnejn imtella’

OpenAPI Markdown

Open model · Vidjo

L-ewwel riżultat tiegħek jidher hawn

Ibni talba hawn taħt u ħaddimha biċ-ċavetta API tiegħek. L-outputs jiġu kkupjati fil-ħażna tagħna, miżmuma għal dejjem jew 7 ijiem b’xejn.

Ibni talba

Prezz għal kull sekonda tal-vidjo tal-output tiegħek

Prezz ibbażat fuq l-input tiegħek

minn $0.20 / sekonda ta’ vidjo tal-output

200 krediti tal-API / sekonda ta’ vidjo tal-output · ≈ ₽21.09

Din it-talba: 7.24 sekondi × $0.20 × 1.25 (aktar minn 81 frejm) $1.81 1,810 krediti tal-API · ≈ ₽190.89

Ħaddem · $1.81

Iċċarġjat biss jekk jirnexxi, u rimborżat awtomatikament jekk ifalli.

num_frames prestabbilit 181

resolution prestabbilit 480p

Prezz skont il-livell

rata bażi	$0.20 / sekonda ta’ vidjo tal-output
aktar minn 81 frejm	$0.25 / sekonda ta’ vidjo tal-output
720p	$0.40 / sekonda ta’ vidjo tal-output
720p, aktar minn 81 frejm	$0.50 / 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

Istruzzjonijiet testwali li jiggwidaw il-ġenerazzjoni tal-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.

first_audio_url •meħtieġ

Waqqa’ fajl, jew

URL tal-fajl awdjo għal Person 1.

resolution prestabbilit 480p

Riżoluzzjoni tal-vidjo output; huma appoġġjati biss 480p u 720p.

num_frames prestabbilit 181

Għadd ta’ frejms għall-ġenerazzjoni, minn 81 sa 129, inklużi.

Avvanzat second_audio_url · acceleration · seed · use_only_first_audio · enable_safety_checker

second_audio_url

Waqqa’ fajl, jew

URL tal-fajl awdjo għal Person 2.

acceleration prestabbilit regular

Livell ta’ aċċelerazzjoni applikat waqt il-ġenerazzjoni.

seed prestabbilit 81

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

POST /run/ai-avatar/multi?wait=20 kwotazzjoni → $1.81

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

# 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/ai-avatar/multi?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "first_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
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 = {
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "first_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ai-avatar/multi", 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": "ai-avatar/multi",
      "input": {
        "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
        "first_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "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 AI Avatar Multi

Jieħu immaġni waħda flimkien ma’ `first_audio_url` u `second_audio_url` fakultattiv biex jipproduċi vidjo li fih in-nies fl-istampa jitkellmu wara xulxin. `prompt` meħtieġ jiggwida x-xena. L-output huwa 480p jew 720p, b’`num_frames` minn 41 sa 241. `use_only_first_audio` jillimita r-riżultat għall-ewwel track, u `acceleration` jista’ jkun none, regular jew high.

Parametri

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

IsemTip PrestabbilitPermess Deskrizzjoni

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.

first_audio_urlmeħtieġ

Tipurl · audio

URL tal-fajl awdjo għal Person 1.

second_audio_urlmhux obbligatorju

Tipurl · audio

URL tal-fajl awdjo għal Person 2.

promptmeħtieġ

Tipstring

Istruzzjonijiet testwali li jiggwidaw il-ġenerazzjoni tal-vidjo.

num_framesmhux obbligatorju

Tipinteger

Prestabbilit181

41 – 241

Għadd ta’ frejms għall-ġenerazzjoni, minn 81 sa 129, inklużi.

resolutionmhux obbligatorju

Tipenum

Prestabbilit480p

480p720p

Riżoluzzjoni tal-vidjo output; huma appoġġjati biss 480p u 720p.

seedmhux obbligatorju

Tipinteger

Prestabbilit81

0 – 4,294,967,295

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

use_only_first_audiomhux obbligatorju

Tipboolean

Prestabbilitfalse

Jikkontrolla jekk jintużax biss l-ewwel fajl awdjo.

accelerationmhux obbligatorju

Tipenum

Prestabbilitregular

noneregularhigh

Livell ta’ aċċelerazzjoni applikat waqt il-ġenerazzjoni.

enable_safety_checkermhux obbligatorju

Tipboolean

Prestabbilittrue

L-iskrinjar jista’ jiġi rilassat billi jiġi ssettjat għal false, sakemm min jagħmel it-talba jkun awtorizzat.

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": "ai-avatar/multi",
  "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": 1810,
    "usd": "1.81",
    "charged": 1810,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "first_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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
    },
    "seed": 42
  },
  "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.
seed: integerValur ta’ seed applikat waqt il-ġenerazzjoni.

Aktar mudelli: Lipsync u avatars

Għall-aġenti tal-AI: din il-paġna bħala Markdown tinsab fuq https://doitong.com/mt/developers/models/ai-avatar/multi.md. Il-mudelli u l-gwidi kollha: https://doitong.com/developers/llms.txt

L-ewwel riżultat tiegħek jidher hawn

Ibni talba

Ħaddem din it-talba

Dwar AI Avatar Multi

Parametri

Output

Varjanti oħra ta’ AI Avatar

AI Avatar Multi Text Varjanti: 3

AI Avatar Single Text Varjanti: 3

Aktar mudelli: Lipsync u avatars

Kling AI Avatar 2.0 Pro Varjanti: 5

Sync Lipsync 3 Varjanti: 3

VEED Fabric 1.0 Varjanti: 6

Flashhead