Saltar al cuntegna

Heygen v5 Digital Twin

Integrar

ID dal model 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.ru/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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Datotecas sco l'exempel: $1,00 1 000 credits API · ≈ ₽107,58 tias datotecas vegnan mesiradas avant l'execuziun Lantschar sin questa pagina

Obtegna ina clav API
HeyGen Lipsync e avatars Output 4KLipsyncfin a 4k #avatar#digital-twin#talking-avatar#text-to-video

Avatar V digital-twin cun output 4k, WebM transparent, fund, filigrana e subtitles SRT

HeyGen · Video

Tes emprim resultat vegn qua

Construis ina dumonda sutvart e l'exequescha cun tia clav API. Outputs vegnan copiads en nossa memorisaziun, conservads per adina u 7 dis gratuitamain.

Construir ina dumonda

Ils controls vegnan generads dal schema dal model. Il code e ​​il pretsch s'actualiseschan durant che ti als midas.

Text discurrì per l'avatar; necessari, sche `audio_url` manca.

audio_url
Trametta in datoteca u

Funtauna per la sincronisaziun dals lefs, furnida sco URL d'ina datoteca audio HTTP(S), che remplazza text-to-speech, sche preschenta. En quest cas na vegnan utilisads ni `prompt` ni `voice`.

resolution standard 720p

Preset da resoluziun per l'output generà.

aspect_ratio standard 16:9

Tscherna da la proporziun d'aspect dal video: 'auto' dumonda HeyGen da leger e mantegnair la proporziun da la funtauna, utilisond '16:9' sch'ella na po betg vegnir legida. Las proporziuns explicitamain tschernidas èn '16:9', '9:16', '4:5', '5:4', e '1:1'.

Avanzà fit · output_format · avatar · voice · remove_background · caption · enable_safety_checker · background · watermark
fit standard cover

Tscherna l'inquadratura da l'avatar: 'cover' emplenescha il frame d'output, ma po tagliar l'avatar, entant che 'contain' mussa l'avatar entir, ma po agiuntar barras nairas.

output_format standard mp4

Selecziun dal container video, cun `webm` che permetta transparenza grazia a l'allontanament automatic dal fund; en quel modus n'ha `background` nagin effect.

standard Abigail Sofa Front

Num che identifitgescha in avatar adattà per Avatar V.

standard Warm Pro Narrator

Selecziun da la vusch da l'avatar tenor num per text-to-speech; vala mo senza `audio_url`.

Cuvrida dal fund plazzada opziunalmain davos l'avatar, exceptà cun `output_format='webm'`: in output webm transparent ignorescha questa configuraziun.

Maletg opziunal utilisà sco filigrana en il video generà.

POST /run/heygen/avatar5/digital-twin?wait=20 calculaziun → $1,00
# 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/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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Executar questa dumonda

Tia clav resta en quest browser: ella vegn tramessa mo al Doitong API e memorisada (localStorage) mo sch'ella scheccas Tiar a memoria. Obtegnair ina clav API

Davart Heygen v5 Digital Twin

Crea in video cun avatar discurrint a partir da text (`prompt` e `voice`) u d'in `audio_url` per la sincronisaziun da las levzas. Tscherni in `avatar` numnà, in modus `fit` da contain u cover, e ina resoluziun da 720p, 1080p u 4k. `output_format` po esser mp4 u webm; webm è transparent. Las opziuns includan la cumposiziun dal sfond, ina surposiziun da filigrana ed ina datoteca SRT laterala cun descripziuns.

Parameters

Invia u il num canonic u il num nativ, betg omaduas. Nums canonics

NumTip StandardPermess Descripziun
avataropziunal
Tipstring | null
StandardAbigail Sofa Front
Num che identifitgescha in avatar adattà per Avatar V.
promptopziunal
Tipstring | null
Text discurrì per l'avatar; necessari, sche `audio_url` manca.
voiceopziunal
Tipenum
StandardWarm Pro Narrator
Warm Pro NarratorChill BrianIvyJohn DoeMonika SogamHope Archer BrittneyPatrickDavid CastlemoreMichael CAdam Stone JuniperCassidy Jessica Anne BogartArabella
+86 dapliAndrewSpuds 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
Selecziun da la vusch da l'avatar tenor num per text-to-speech; vala mo senza `audio_url`.
audio_urlopziunal audio
Tipurl · audio
Funtauna per la sincronisaziun dals lefs, furnida sco URL d'ina datoteca audio HTTP(S), che remplazza text-to-speech, sche preschenta. En quest cas na vegnan utilisads ni `prompt` ni `voice`.
fitopziunal
Tipenum
Standardcover
containcover
Tscherna l'inquadratura da l'avatar: 'cover' emplenescha il frame d'output, ma po tagliar l'avatar, entant che 'contain' mussa l'avatar entir, ma po agiuntar barras nairas.
remove_backgroundopziunal
Tipboolean
Standardfalse
Allontanament dal fund per l'avatar; disponibel mo per avatars che sustegnan matting.
backgroundopziunal
Tipobject
Cuvrida dal fund plazzada opziunalmain davos l'avatar, exceptà cun `output_format='webm'`: in output webm transparent ignorescha questa configuraziun.
background.typeopziunal
Tipenum
Standardcolor
colorimage
Tip da fund: `color` inditgescha ina colur esadecimala solid, entant che `image` inditgescha ina URL d'in maletg.
background.valueopziunal
Tipstring
Standard#FFFFFF
Cuntansch dal fund: ina colur esadecimala, sche il tip è `color`, u ina URL HTTP(S), sche il tip è `image`.
watermarkopziunal
Tipobject
Maletg opziunal utilisà sco filigrana en il video generà.
watermark.image_urlobligatori
Tipurl · image
URL HTTP(S) dal maletg da la filigrana, per l'overlay en il video.
watermark.scaleopziunal
Tipnumber | null
≤ 2, > 0
Grondezza da la filigrana en relaziun cun il video, pli gronda che 0.0 e fin a 2.0.
watermark.opacityopziunal
Tipnumber | null
0 – 1
Transparenza da la filigrana: 0.0 è cumplettamain transparent e 1.0 cumplettamain opac.
watermark.placementopziunal
Tipenum
top-lefttop-rightbottom-leftbottom-right
Posiziun da la filigrana entaifer il video.
captionopziunal
Tipboolean
Standardfalse
Definescha la generaziun d'ina datoteca da suttitels SRT separada che accumpogna il video.
output_formatopziunal
Tipenum
Standardmp4
mp4webm
Selecziun dal container video, cun `webm` che permetta transparenza grazia a l'allontanament automatic dal fund; en quel modus n'ha `background` nagin effect.
resolutionopziunal
Tipenum
Standard720p
720p1080p4k
Preset da resoluziun per l'output generà.
aspect_ratioopziunal
Tipenum
Standard16:9
16:99:164:55:41:1auto
Tscherna da la proporziun d'aspect dal video: 'auto' dumonda HeyGen da leger e mantegnair la proporziun da la funtauna, utilisond '16:9' sch'ella na po betg vegnir legida. Las proporziuns explicitamain tschernidas èn '16:9', '9:16', '4:5', '5:4', e '1:1'.
enable_safety_checkeropziunal
Tipboolean
Standardtrue
La controlla po vegnir schluccada cun definir false, premess che l'appelant saja autorisà.
obligatori Num canonic, er acceptà

Ils parameters da datotecas acceptan ina URL publica https://, ina URI data: fin a 10 MB u il file_url d'ina chargiada. Datotecas

Output

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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Tias datotecas, tia decisiunMintga outputs[].url è ina copia en nossa memorisaziun: conservada per adina (pajà per GB-mes) u 7 dis gratuitamain, tenor la configuraziun dal conto u ?storage=.
La medema structura per mintga modeltype, url, content_type, width, height e duration, tant per maletgs sco per video e audio. output è l'object da resultat dal model sez.
Champs da l'output
video
object {url, content_type, file_name, file_size}Datoteca video producida da Avatar V.
caption_file
object {url, content_type, file_name, file_size} | nullDatoteca da suttitels SRT producida, sche `caption=True`, sch'il servetsch furnescha ina tala.

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/heygen/avatar5/digital-twin.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt