Saltar al cuntegna

Bytedance Omnihuman V2

Integrar

ID dal model bytedance/omnihuman/v2
# 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/bytedance/omnihuman/v2?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",
    "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"

Datotecas sco l'exempel: $1,05 1 050 credits API tias datotecas vegnan mesiradas avant l'execuziun Lantschar sin questa pagina

Obtegna ina clav API
ByteDance Lipsync e avatars Lipsync #image-to-video

OmniHuman 2 tracta audio pli lung da 4 fin 300 secundas, cun in prompt da scena multiling opziunal

ByteDance · 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.

Controlla precisa da la scena, dal moviment e da la camera tras in prompt da text facultativ scrit en ina lingua sustegnida: indonais, spagnol (mexican), corean, giapunais, englais u chinais.

•obligatori image_url
Trametta in datoteca u

URL che mussa al maletg dal qual il video vegn generà. Il maletg sto avair omaduas dimensiuns entaifer 300–6000 pixels e in quotiant ladezza/otezza entaifer 0.4–2.5. Las datotecas èn limitadas a 30 MB e ston utilisar il format jpeg, png, webp, bmp, tiff, gif, heic u heif.

•obligatori audio_url
Trametta in datoteca u

Furnescha l'audio da funtauna dal video tras in URL che mussa ad ina datoteca cun ina durada da 4–300 secundas. La datoteca sto esser wav u mp3 e betg pli gronda che 15 MB.

POST /run/bytedance/omnihuman/v2?wait=20 calculaziun → $1,05
# 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/bytedance/omnihuman/v2?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",
    "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"

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 Bytedance Omnihuman V2

Transformescha in maletg da persuna ed ina datoteca audio en in video parlant. L'audio sto esser wav u mp3, fin a 15 MB, tranter 4 e 300 secundas. Il maletg po avair fin a 30 MB, cun varts da 300 fin a 6000 pixels. In `prompt` opziunal dirigia scena, moviment e camera en pliras linguas sustegnidas.

Parameters

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

NumTip StandardPermess Descripziun
promptopziunal
Tipstring | null
Controlla precisa da la scena, dal moviment e da la camera tras in prompt da text facultativ scrit en ina lingua sustegnida: indonais, spagnol (mexican), corean, giapunais, englais u chinais.
image_urlobligatori image
Tipurl · image
URL che mussa al maletg dal qual il video vegn generà. Il maletg sto avair omaduas dimensiuns entaifer 300–6000 pixels e in quotiant ladezza/otezza entaifer 0.4–2.5. Las datotecas èn limitadas a 30 MB e ston utilisar il format jpeg, png, webp, bmp, tiff, gif, heic u heif.
audio_urlobligatori audio
Tipurl · audio
Furnescha l'audio da funtauna dal video tras in URL che mussa ad ina datoteca cun ina durada da 4–300 secundas. La datoteca sto esser wav u mp3 e betg pli gronda che 15 MB.
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": "bytedance/omnihuman/v2",
  "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": 1050,
    "usd": "1.05",
    "charged": 1050,
    "refunded": 0
  },
  "input": {
    "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
    },
    "duration": 5
  },
  "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"
  }
}
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 resultanta.
duration
number

Dapli models: Lipsync e avatars

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/bytedance/omnihuman/v2.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt