Ruka hadi kwenye maudhui

AI Avatar Multi

Unganisha

Kitambulisho cha modeli 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.com/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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Faili kama mfano: $ 1.81 salio za API 1,810 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
Open model Usawazishaji wa Midomo na Avatari Usawazishaji wa midomohadi 720p #stylized#transform

Huhuisha picha tulivu kuwa video ya mazungumzo ya watu wawili inayoendeshwa na rekodi moja au mbili za sauti zilizopakiwa

Open model · Video

Tokeo lako la kwanza linaonekana hapa

Unda ombi hapa chini na uliendeshe kwa ufunguo wako wa API. Matokeo yanakiliwa kwenye hifadhi yetu, yakihifadhiwa milele au 7 siku bila malipo.

Unda ombi

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

•inahitajika

Maelekezo ya maandishi yanayoongoza uzalishaji wa video.

•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.

•inahitajika
Dondosha faili, au

URL ya faili ya sauti ya Person 1.

resolution chaguomsingi 480p

Mwonekano wa video ya tokeo; 480p na 720p pekee ndizo zinazotumika.

chaguomsingi 181

Idadi ya fremu za uzalishaji, kutoka 81 hadi 129, ikijumuisha mipaka.

Ya kina second_audio_url · acceleration · seed · use_only_first_audio · enable_safety_checker
Dondosha faili, au

URL ya faili ya sauti ya Person 2.

acceleration chaguomsingi regular

Kiwango cha kuongeza kasi kinachotumika wakati wa uzalishaji.

chaguomsingi 81

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

POST /run/ai-avatar/multi?wait=20 makadirio → $ 1.81
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Endesha ombi hili

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

Kuhusu AI Avatar Multi

Hupokea picha moja pamoja na `first_audio_url` na `second_audio_url` ya hiari ili kutoa video ambayo watu kwenye picha huzungumza kwa zamu. `prompt` inayohitajika huongoza tukio. Matokeo ni 480p au 720p, yenye `num_frames` kutoka 41 hadi 241. `use_only_first_audio` huweka matokeo kwenye rekodi ya kwanza pekee, na `acceleration` inaweza kuwa none, regular au high.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo
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.
first_audio_urlinahitajika
Ainaurl · audio
URL ya faili ya sauti ya Person 1.
second_audio_urlsi lazima
Ainaurl · audio
URL ya faili ya sauti ya Person 2.
promptinahitajika
Ainastring
Maelekezo ya maandishi yanayoongoza uzalishaji wa video.
num_framessi lazima
Ainainteger
Chaguomsingi181
41 – 241
Idadi ya fremu za uzalishaji, kutoka 81 hadi 129, ikijumuisha mipaka.
resolutionsi lazima
Ainaenum
Chaguomsingi480p
480p720p
Mwonekano wa video ya tokeo; 480p na 720p pekee ndizo zinazotumika.
seedsi lazima
Ainainteger
Chaguomsingi81
0 – 4,294,967,295
Seed inayofanya uzalishaji uweze kurudiwa. Kuiweka kuwa None huchagua seed bila mpangilio.
use_only_first_audiosi lazima
Ainaboolean
Chaguomsingifalse
Hudhibiti ikiwa faili ya sauti ya kwanza pekee ndiyo itatumika.
accelerationsi lazima
Ainaenum
Chaguomsingiregular
noneregularhigh
Kiwango cha kuongeza kasi kinachotumika wakati wa uzalishaji.
enable_safety_checkersi lazima
Ainaboolean
Chaguomsingitrue
Ukaguzi unaweza kulegezwa kwa kuweka false, ikiwa mpigaji simu ameidhinishwa.
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": "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/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.
seed
integerThamani ya seed inayotumika wakati wa uzalishaji.

Miundo zaidi: Usawazishaji wa Midomo na Avatari

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/ai-avatar/multi.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt