Saltar al cuntegna

Mirage Avatar X

Integrar

ID dal model mirage-api/avatar-x/reference-to-video
# 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/mirage-api/avatar-x/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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: $3,00 3 000 credits API tias datotecas vegnan mesiradas avant l'execuziun Lantschar sin questa pagina

Obtegna ina clav API
Mirage Lipsync e avatars Inputs da referenzaLipsync #avatar#talking-head

Video Avatar X da testa discurrenta, manà da tes audio e d'ina imagiun, in video u ina referenza d'avatar da catalog

Mirage · 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.

•obligatori audio_url
Trametta in datoteca u

Adressa HTTPS publica per l’audio che gida a generar il video, accessibla senza headers d’autorisaziun u cookies. Ils formats audio acceptads èn FLAC, Opus u Vorbis, AAC u ALAC, PCM WAV u AIFF, e MP3. La datoteca sto cuntegnair in sulet stream mono u stereo, durar 3–180 secundas, occupar maximalmain 64 MiB ed avair ina frequenza da sampling da 8–48 kHz.

Avanzà video_reference_url · avatar · image_reference_url

URL HTTPS dal video da referenza, accessibel publicamain senza headers d’autorisaziun u cookies, per ina datoteca che cuntegna exactamain in stream video e almain in segment adattà d’1 secunda. L’audio vegn ignorà. Las datotecas acceptadas cumbineschan .mp4, .mov u .m4v cun H.264, H.265/HEVC u ProRes, u .webm cun VP8 u VP9; la durada sto esser da 1 a 120 secundas, la grondezza na dastga betg surpassar 1 GiB, e la relaziun d’aspect da la visualisaziun sto esser entaifer 5% da 9:16 u 16:9. Sche image_reference_url è era furnì, ha il video la prioritad.

Selecziun visuala da stock utilisada mo sche nagin maletg u video da referenza vegn furnì; None e la valur standard laschan ometter la valur. L’audio na vegn mai furnì da questa visuala e vegn adina da audio_url. Per tscherner ina visuala, previsualisai las opziuns en il [catalog d’avatars](https://captions.ai/help/docs/api/actor-catalog) e copiai sia valur Avatar exacta.

URL HTTPS d’in maletg da referenza, accessibel publicamain senza cookies u headers d’autorisaziun; furnir video_reference_url fa ignorar el. Accepta in sulet maletg static en format .jpg, .jpeg, .png u .webp, limità a 25 MiB e 25 megapixels. L’ur pli curt sto mesirar almain 512 px e nagin ur na dastga surpassar 8192 px; la relaziun d’aspect sto esser entaifer 5% da 9:16 u 16:9.

POST /run/mirage-api/avatar-x/reference-to-video?wait=20 calculaziun → $3,00
# 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/mirage-api/avatar-x/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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 Mirage Avatar X

Crea in video d'avatar cun sincronisaziun da las levzas da `audio_url` (3 fin a 180 secundas). L'aspect visual vegn da `video_reference_url`, `image_reference_url` u d'in `avatar` da catalog; la referenza video ha precedenza sur l'imagiun, sch'ellas vegnan dadas omaduas. L'opziun avatar furnescha mo elements visuals, betg audio. Las URLs da referenza ston esser accessiblas publicamain sur HTTPS.

Parameters

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

NumTip StandardPermess Descripziun
audio_urlobligatori audio
Tipurl · audio
Adressa HTTPS publica per l’audio che gida a generar il video, accessibla senza headers d’autorisaziun u cookies. Ils formats audio acceptads èn FLAC, Opus u Vorbis, AAC u ALAC, PCM WAV u AIFF, e MP3. La datoteca sto cuntegnair in sulet stream mono u stereo, durar 3–180 secundas, occupar maximalmain 64 MiB ed avair ina frequenza da sampling da 8–48 kHz.
video_reference_urlopziunal
Tipstring | null
URL HTTPS dal video da referenza, accessibel publicamain senza headers d’autorisaziun u cookies, per ina datoteca che cuntegna exactamain in stream video e almain in segment adattà d’1 secunda. L’audio vegn ignorà. Las datotecas acceptadas cumbineschan .mp4, .mov u .m4v cun H.264, H.265/HEVC u ProRes, u .webm cun VP8 u VP9; la durada sto esser da 1 a 120 secundas, la grondezza na dastga betg surpassar 1 GiB, e la relaziun d’aspect da la visualisaziun sto esser entaifer 5% da 9:16 u 16:9. Sche image_reference_url è era furnì, ha il video la prioritad.
avataropziunal
Tipenum
NoneAyeshaAyesha (16:9)FarhanFarhan (16:9)GiuliaGiulia (16:9)JasmineJasmine (16:9)LukeLuke (16:9)MayaMaya (16:9)MichaelMichael (16:9)Neha
+5 dapliNeha (16:9)TariqTariq (16:9)ValerieValerie (16:9)
Selecziun visuala da stock utilisada mo sche nagin maletg u video da referenza vegn furnì; None e la valur standard laschan ometter la valur. L’audio na vegn mai furnì da questa visuala e vegn adina da audio_url. Per tscherner ina visuala, previsualisai las opziuns en il [catalog d’avatars](https://captions.ai/help/docs/api/actor-catalog) e copiai sia valur Avatar exacta.
image_reference_urlopziunal
Tipstring | null
URL HTTPS d’in maletg da referenza, accessibel publicamain senza cookies u headers d’autorisaziun; furnir video_reference_url fa ignorar el. Accepta in sulet maletg static en format .jpg, .jpeg, .png u .webp, limità a 25 MiB e 25 megapixels. L’ur pli curt sto mesirar almain 512 px e nagin ur na dastga surpassar 8192 px; la relaziun d’aspect sto esser entaifer 5% da 9:16 u 16:9.
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": "mirage-api/avatar-x/reference-to-video",
  "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": 3000,
    "usd": "3.00",
    "charged": 3000,
    "refunded": 0
  },
  "input": {
    "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
    }
  },
  "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}

Dapli models: Lipsync e avatars

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/mirage-api/avatar-x/reference-to-video.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt