Ruka hadi kwenye maudhui

Heygen v5 Digital Twin

Unganisha

Kitambulisho cha modeli heygen/avatar5/digital-twin
# 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/heygen/avatar5/digital-twin?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",
    "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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Faili kama mfano: $ 1.00 salio za API 1,000 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
HeyGen Usawazishaji wa Midomo na Avatari Pato la 4KUsawazishaji wa midomohadi 4k #avatar#digital-twin#talking-avatar#text-to-video

Pacha wa kidijitali wa avatari V wenye tokeo la 4k, WebM yenye uwazi, mandharinyuma, alama ya maji na maelezo mafupi ya SRT

HeyGen · 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.

Maandishi ya matamshi ya avatar; yanahitajika ikiwa `audio_url` haijatolewa.

audio_url
Dondosha faili, au

Chanzo cha kusawazisha midomo kinachotolewa kama URL ya faili ya sauti ya HTTP(S), kikibadilisha kubadilisha maandishi kuwa sauti kinapopatikana. `prompt` wala `voice` haitumiki katika hali hiyo.

resolution chaguomsingi 720p

Mipangilio chaguomsingi ya mwonekano wa tokeo lililozalishwa.

aspect_ratio chaguomsingi 16:9

Uteuzi wa uwiano wa picha wa video: 'auto' huomba HeyGen isome na ihifadhi uwiano wa chanzo, ikitumia '16:9' ikiwa haiwezi. Chaguo dhahiri za uwiano ni '16:9', '9:16', '4:5', '5:4', na '1:1'.

Ya kina fit · output_format · avatar · voice · remove_background · caption · enable_safety_checker · background · watermark
fit chaguomsingi cover

Chagua fremu ya avatar: 'cover' hujaza fremu ya tokeo lakini inaweza kukata avatar, ilhali 'contain' huonyesha avatar yote lakini inaweza kuongeza kingo nyeusi.

output_format chaguomsingi mp4

Uteuzi wa kontena la video, ambapo `webm` huwezesha uwazi kupitia uondoaji wa mandharinyuma kiotomatiki; katika hali hiyo, `background` haina athari.

chaguomsingi Abigail Sofa Front

Jina linalomtambulisha avatar anayestahiki Avatar V.

chaguomsingi Warm Pro Narrator

Uteuzi wa sauti ya avatar kwa jina kwa ajili ya kubadilisha maandishi kuwa sauti; hutumika tu bila `audio_url`.

Tabaka la mandharinyuma linalowekwa kwa hiari nyuma ya avatar, isipokuwa kwa `output_format='webm'`: tokeo la webm lenye uwazi hupuuza mpangilio huu.

Picha ya hiari inayotumika kama watermark juu ya video iliyozalishwa.

POST /run/heygen/avatar5/digital-twin?wait=20 makadirio → $ 1.00
# 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/heygen/avatar5/digital-twin?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",
    "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.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 Heygen v5 Digital Twin

Huunda video ya avatari inayozungumza kutoka kwa maandishi (`prompt` na `voice`) au kutoka `audio_url` kwa usawazishaji wa midomo. Chagua `avatar` yenye jina, hali ya `fit` ya contain au cover, na mwonekano wa 720p, 1080p au 4k. `output_format` inaweza kuwa mp4 au webm; webm huwa na uwazi. Chaguo ni pamoja na uunganishaji wa mandharinyuma, wekeleo la alama ya maji na faili ya maelezo mafupi ya SRT ya pembeni.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo
avatarsi lazima
Ainastring | null
ChaguomsingiAbigail Sofa Front
Jina linalomtambulisha avatar anayestahiki Avatar V.
promptsi lazima
Ainastring | null
Maandishi ya matamshi ya avatar; yanahitajika ikiwa `audio_url` haijatolewa.
voicesi lazima
Ainaenum
ChaguomsingiWarm Pro Narrator
Warm Pro NarratorChill BrianIvyJohn DoeMonika SogamHope Archer BrittneyPatrickDavid CastlemoreMichael CAdam Stone JuniperCassidy Jessica Anne BogartArabella
+86 zaidiAndrewSpuds Oxley Grace ElderHelenCanyon RiversDerya - Lifelike - Excited 🤩Mellow MarcusJack Sterling - Broadcaster 🎙️Brenda - UGC - 1.mp4ReidReaganTerryJennyRadio RickDeniseTim in car - Excited 🤩IskanderThompsonDelicate Daisy - Excited 🤩KingstonGeorge UGC 1Bold BlakeJaneExpressive EvanMarianne - IAAaronModern Recipe Host - Voice 1WillowCute Chloe - Friendly 😊RafaelJune - LifelikeCrisp ChloeSlick SimonNassim - InformativeBaritone BenMaxwellEllie Faye - Excited 🤩MilaniFeisty Fiona - Excited 🤩Professor DeanRose - UGC - 1.mp4ShonaHudson WilderAnn - IAAlastair KensingtonOxleyChristinaAndrew Rizz PeytonGerardo - OutdoorChloe - LifelikeStephanieAnthony - IASignal - Voice 1LucaLisa - Voice 1T.W.TuckerJack Sullivan - Serious 😐WinterMireia - LifelikeGeorgiaStellaMasha - LifelikeCharming Charles - Friendly 😊SerenityAnnie - ExcitedRalphBethanyDominicMason FinnLeenaVeteran VictorTamaraNik PublicCalm ChloeSevikReillyRaulImposing IanRelaxed RayDexter - ProfessionalRelaxed RickEdwinRupert BlackwoodGinnyHope
Uteuzi wa sauti ya avatar kwa jina kwa ajili ya kubadilisha maandishi kuwa sauti; hutumika tu bila `audio_url`.
audio_urlsi lazima audio
Ainaurl · audio
Chanzo cha kusawazisha midomo kinachotolewa kama URL ya faili ya sauti ya HTTP(S), kikibadilisha kubadilisha maandishi kuwa sauti kinapopatikana. `prompt` wala `voice` haitumiki katika hali hiyo.
fitsi lazima
Ainaenum
Chaguomsingicover
containcover
Chagua fremu ya avatar: 'cover' hujaza fremu ya tokeo lakini inaweza kukata avatar, ilhali 'contain' huonyesha avatar yote lakini inaweza kuongeza kingo nyeusi.
remove_backgroundsi lazima
Ainaboolean
Chaguomsingifalse
Uondoaji wa mandharinyuma ya avatar; unapatikana tu kwa avatar zinazotumia matting.
backgroundsi lazima
Ainaobject
Tabaka la mandharinyuma linalowekwa kwa hiari nyuma ya avatar, isipokuwa kwa `output_format='webm'`: tokeo la webm lenye uwazi hupuuza mpangilio huu.
background.typesi lazima
Ainaenum
Chaguomsingicolor
colorimage
Aina ya mandharinyuma: `color` hubainisha rangi thabiti ya heksadesimali, huku `image` ikibainisha URL ya picha.
background.valuesi lazima
Ainastring
Chaguomsingi#FFFFFF
Maudhui ya mandharinyuma: rangi ya heksadesimali aina ikiwa ni `color`, au URL ya HTTP(S) aina ikiwa ni `image`.
watermarksi lazima
Ainaobject
Picha ya hiari inayotumika kama watermark juu ya video iliyozalishwa.
watermark.image_urlinahitajika
Ainaurl · image
URL ya picha ya watermark inayotumia HTTP(S), kwa kuiweka juu ya video.
watermark.scalesi lazima
Ainanumber | null
≤ 2, > 0
Ukubwa wa watermark kulingana na video, zaidi ya 0.0 hadi 2.0.
watermark.opacitysi lazima
Ainanumber | null
0 – 1
Kiwango cha uwazi wa watermark: 0.0 ni uwazi kamili na 1.0 si wazi kabisa.
watermark.placementsi lazima
Ainaenum
top-lefttop-rightbottom-leftbottom-right
Nafasi ya watermark ndani ya video.
captionsi lazima
Ainaboolean
Chaguomsingifalse
Hudhibiti uzalishaji wa faili tofauti la manukuu ya SRT linaloambatana na video.
output_formatsi lazima
Ainaenum
Chaguomsingimp4
mp4webm
Uteuzi wa kontena la video, ambapo `webm` huwezesha uwazi kupitia uondoaji wa mandharinyuma kiotomatiki; katika hali hiyo, `background` haina athari.
resolutionsi lazima
Ainaenum
Chaguomsingi720p
720p1080p4k
Mipangilio chaguomsingi ya mwonekano wa tokeo lililozalishwa.
aspect_ratiosi lazima
Ainaenum
Chaguomsingi16:9
16:99:164:55:41:1auto
Uteuzi wa uwiano wa picha wa video: 'auto' huomba HeyGen isome na ihifadhi uwiano wa chanzo, ikitumia '16:9' ikiwa haiwezi. Chaguo dhahiri za uwiano ni '16:9', '9:16', '4:5', '5:4', na '1:1'.
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": "heygen/avatar5/digital-twin",
  "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": 1000,
    "usd": "1.00",
    "charged": 1000,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "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
    },
    "caption_file": {
      "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.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 na Avatar V.
caption_file
object {url, content_type, file_name, file_size} | nullFaili la manukuu ya SRT linalozalishwa wakati `caption=True`, ikiwa huduma inatoa moja.

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/heygen/avatar5/digital-twin.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt