ᡤᡝᠯᡳ ᡩᡝ ᠵᡠᠸᡝᠨ

Bytedance Omnihuman V2

ᠵᡠᠸᡝᠪᡠᠮᠪᡳ

ᠮᠣᡩᡝᠯ id 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"

ᠵᠠᠨᡳ ᡥᠠᠯᠠᠮᠠ ᡥᡡᠯᠠᠨᡳ ᡶᡳᠯᡝ: $1.05 1,050 API ᠺᠷᡝᡩᡳᠲ ᠰᡳᠨᡳ ᡶᡳᠯᡝ ᠵᠠᠯᡤᠠᠨ ᠠᠰᡠᠮᠪᡳᠨᡳ ᠠᠯᡳᠮᠪᡳ ᡝᡵᡝ ᠵᠠᠯᡳᠨᡩᡝ ᠠᠰᡠᠮᠪᡳ

API ᡩᠠᠮᡠᠨ ᡤᠠᠯᠠ
ByteDance ᠠᠮᡤᠠ ᡩᡝ ᠰᡠᠨᡤᠠ ᠠᠮᡤᠠ ᡩᡝ ᠰᡠᠨᡤᠠ #image-to-video#lipsync

OmniHuman 2 ᠵᡝᠯᡤᡳ ᠠᠶᠣᠣ 4 ᠴᡳ 300 ᠰᡝᡴᡠᠨᡩ ᠪᡝ ᠠᠪᡠᠮᡝ ᠣᠮᠪᡳ᠂ ᠠᠮᠠᠯᠠᠯᠠᠮᡝ ᠣᠯᠣᠨ ᡥᡝᠯᡝᠨ ᡳ ᠵᠠᠯᡠ ᠪᡳ

ByteDance · ᠰᡠᠨᡤᠠ

ᡳᠨᡝ ᡝᠮᡠᠨᡳᠩᡤᡝ ᡝᡵᡝᠮᡝ ᡩᡝ

ᡝᡵᡝ ᠵᡠᠯᡝᠨ ᡩᡝ ᡤᡝᡪᡳᠯᡝᠨ ᠪᠠᠶᠠᠨᠠᠮᡝ ᠠᠮᡪᠠᠯᠠ ᡶᡳᠯᡝᠮᡝ ᠪᡝᠶᡝᠮᡝ᠃ API ᠵᡳᡵᡤᠠᡳ ᡤᠠᡳᡥᠠᡩᡝ ᡤᡝᡪᡳᠯᡝᠨ ᠵᠠᠯᠠᠨᠠᠮᡝ ᠪᡠᠶᡝᠮᡝ ᠮᡠᠰᡝᡳ ᠰᡠᠯᡠᠨᡩᡝ ᠪᠠᠶᠠᠨᠠᠮᡝ᠂ ᠝ᠮᡤᡳ ᠮᡠᠰᡝ ᠠᠶᠠᠨ 7 ᡥᠠᠨ ᠰᠠᡳᠨᠠᠮᡝ᠃

ᡤᡳᠰᡠᠨ ᠪᡠᠶᡝᠮᡝ

ᠵᠠᡴᡠᠨᡳ ᠵᡠᠯᡝ ᡩᡝᡵᡤᡳ ᡩᡝᠪᡝᠰᡠᠮᡝ ᠵᡠᠯᡤᡝ ᠪᡠᠶᡝᠮᡝ᠈ ᡳᠨᡳ ᡤᡳᠰᡠᠨ ᠪᠠᡳ ᡝᠨᡝᠩᡤᡳ ᠠᠮᠪᡳ

ᠵᠠᠯᠠᠨᡳ ᠰᠠᠮᡝ, ᠮᡠᠶᠠᠨ ᠣᠴᡳ ᠵᠠᠯᠠᠨ ᠵᡠᠯᡝᠮᡝᠨᡳ ᠵᠠᠯᠠᠨ; ᠰᠠᠶᠠᠨ ᡥᡡᠯᠠᠨ ᠪᡝ ᠵᡝᠮᡝ ᠵᡠᠯᡝᠮᡝ ᠵᠠᠯᠠᠨ ᠣᠴᡳ Indonesian, Spanish (Mexican), Korean, Japanese, English, ᠣᠴᡳ Chinese.

•ᡴᠠᠷᠠᡴᡡ image_url
ᠪᡠᠮᠪᡳ ᡝᠮᡠ ᡩᠠᡵᠠᠮᡝ

ᠰᡠᠨᡤᠠ ᠪᡠᠶᡝᠮᡝ ᠪᡝᠶᡝ ᠵᠠᠯᠠᠨᡳ ᡤᠠᠳᠠᠨᡳ ᡠᠯᡤᡳᠶᡝᠨ ᡩᡠᠯᡝᠮᠪᡳ. ᡤᠠᠳᠠᠨᡳ ᡝᠮᡠ ᡩᡝᡵᡝᠩᡤᡝ 300–6000 ᠫᡳᡴᠰᡝᠯ ᠪᡳᠮᡝ, ᡤᠣᠯᠣ ᠪᠣᠶᠣ ᠵᠠᠯᠠᠨᡳ ᠬᡠᠪᠴᡳᠶᡝ 0.4–2.5 ᡳ ᠵᠠᠰᡝ ᠪᡳᠮᡠᠰᡠ. ᡶᡳᠯᡝ 30 MB ᡳ ᠣᠴᡳᠨ ᡝᠮᡤᡝᠨ ᠪᡳᠮᡝ jpeg, png, webp, bmp, tiff, gif, heic ᠣᠴᡳ heif ᠵᠠᠪᠰᡠᠨ ᠪᡳᠮᡠᠰᡠ.

•ᡴᠠᠷᠠᡴᡡ audio_url
ᠪᡠᠮᠪᡳ ᡝᠮᡠ ᡩᠠᡵᠠᠮᡝ

ᠰᡠᠨᡤᠠᠨᡳ ᡤᡳᠰᡠᠨᡳ ᡝᡵᡝᠮᡝ ᠪᡠᠮᡝ URL ᠪᡝ ᡶᡳᠯᡝᠮᡝ ᠰᡝᡴᡠᠨᡩ 4–300 ᠪᡳᠮᡝ ᠵᠠᠯᠠᠨᡩᠠᠮᡝ. ᡶᡳᠯᡝ ᡳᠨᡠ wav ᠣᠴᡳ mp3 ᠪᡳᠮᡝ 15 MB ᠵᠠᠰᡝ ᠣᠴᡳᠨ ᠪᡳᠮᡠᠰᡠ.

POST /run/bytedance/omnihuman/v2?wait=20 ᠵᠠᠯᡳᠨ → $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"

ᡝᠨᡳ ᠵᠠᠯᡳᠨ ᠪᡝ ᠵᠠᠯᠠᠨᠠᠮᡝ

ᡳᠨᡝ ᠵᠠᠯᠠᠨ ᡝᡵᡝ ᠪᡠᡵᡝᠪᡝᡵᡳ ᡩᡝ ᠪᡳᠮᡝ᠈ Doitong API ᡩᡝ ᠵᡝᠯᡤᡳ ᡩᠠᡵᠠᠮᡝ᠈ Remember ᠵᡠᠯᡝᠮᡝ ᡤᡳᠯᠠᠮᡝ localStorage ᡩᡝ ᠰᡠᠯᡝᠮᡝ ᠪᡳᠮᡝ API ᠵᠠᠯᠠᠨ ᠠᠪᠠᠮᡝ

Bytedance Omnihuman V2 ᡠᡵᡝᠮᡝ

ᡝᠮᡠ ᠵᠠᠯᡳᠨ ᡤᠠᡩᠠᠨ ᡝᠮᡝ ᡤᡳᠰᡠᠨ ᡳ ᡶᡳᠯᡝ ᠠᠴᠠ ᡤᡳᠰᡠᠨ ᠵᠠᠯᡳᠨ ᠰᡠᠨᡤᠠ ᠪᡠᠶᡝᠮᡝ. ᡤᡳᠰᡠᠨ wav ᡝᠮᡝ mp3᠂ 15 MB ᡩᡝᠴᡳ ᠣᠴᡳᠮᠪᡝᠴᡳ᠂ 4 ᠠᠴᠠ 300 ᠰᡝᡴᡠᠨᡩ. ᡤᠠᡩᠠᠨ 30 MB ᡩᡝᠴᡳ᠂ ᡝᠮᡝᠨ ᡳ ᠵᠠᠯᠠᠨ 300 ᠠᠴᠠ 6000 ᠫᡳᡴᠰᡝᠯ. ᠵᡠᠯᡝ `prompt` ᡩᡝ ᠵᡠᠰᡳᠯᡝᠨ ᡳ ᠣᠷᠣᠨ᠂ ᡝᠯᡝᠨ ᡝᠮᡝ ᠵᠠᠯᡳᠨ ᡩᡝ ᠵᠠᠯᡠᠪᡠᠮᡝ.

ᠵᠠᡴᡠᠨ

ᠵᠠᡴᡠᠨᡳ ᡤᡳᠰᡠᠨ ᠵᡝᠯᡤᡳ ᠠᠪᠠᠮᠪᡳ᠈ ᠨᡝᠮᡝ ᠮᡠᠰᡝ ᡠᠯᠠᠮᠪᡳ ᠵᠠᡴᡠᠨᡳ ᡤᡳᠰᡠᠨ

ᠵᡝᡵᡤᡳᡠᠯᠠᠮᡝ ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝᠠᠪᠠᠮᡝ ᠵᠠᠪᡠᠨ ᠵᠠᠯᠠᠨᡳ ᡤᡳᠰᡠᠨ
promptᠵᡠᠯᡝ
ᡠᠯᠠᠮᡝstring | null
ᠵᠠᠯᠠᠨᡳ ᠰᠠᠮᡝ, ᠮᡠᠶᠠᠨ ᠣᠴᡳ ᠵᠠᠯᠠᠨ ᠵᡠᠯᡝᠮᡝᠨᡳ ᠵᠠᠯᠠᠨ; ᠰᠠᠶᠠᠨ ᡥᡡᠯᠠᠨ ᠪᡝ ᠵᡝᠮᡝ ᠵᡠᠯᡝᠮᡝ ᠵᠠᠯᠠᠨ ᠣᠴᡳ Indonesian, Spanish (Mexican), Korean, Japanese, English, ᠣᠴᡳ Chinese.
image_urlᡴᠠᠷᠠᡴᡡ image
ᡠᠯᠠᠮᡝurl · image
ᠰᡠᠨᡤᠠ ᠪᡠᠶᡝᠮᡝ ᠪᡝᠶᡝ ᠵᠠᠯᠠᠨᡳ ᡤᠠᠳᠠᠨᡳ ᡠᠯᡤᡳᠶᡝᠨ ᡩᡠᠯᡝᠮᠪᡳ. ᡤᠠᠳᠠᠨᡳ ᡝᠮᡠ ᡩᡝᡵᡝᠩᡤᡝ 300–6000 ᠫᡳᡴᠰᡝᠯ ᠪᡳᠮᡝ, ᡤᠣᠯᠣ ᠪᠣᠶᠣ ᠵᠠᠯᠠᠨᡳ ᠬᡠᠪᠴᡳᠶᡝ 0.4–2.5 ᡳ ᠵᠠᠰᡝ ᠪᡳᠮᡠᠰᡠ. ᡶᡳᠯᡝ 30 MB ᡳ ᠣᠴᡳᠨ ᡝᠮᡤᡝᠨ ᠪᡳᠮᡝ jpeg, png, webp, bmp, tiff, gif, heic ᠣᠴᡳ heif ᠵᠠᠪᠰᡠᠨ ᠪᡳᠮᡠᠰᡠ.
audio_urlᡴᠠᠷᠠᡴᡡ audio
ᡠᠯᠠᠮᡝurl · audio
ᠰᡠᠨᡤᠠᠨᡳ ᡤᡳᠰᡠᠨᡳ ᡝᡵᡝᠮᡝ ᠪᡠᠮᡝ URL ᠪᡝ ᡶᡳᠯᡝᠮᡝ ᠰᡝᡴᡠᠨᡩ 4–300 ᠪᡳᠮᡝ ᠵᠠᠯᠠᠨᡩᠠᠮᡝ. ᡶᡳᠯᡝ ᡳᠨᡠ wav ᠣᠴᡳ mp3 ᠪᡳᠮᡝ 15 MB ᠵᠠᠰᡝ ᠣᠴᡳᠨ ᠪᡳᠮᡠᠰᡠ.
ᡴᠠᠷᠠᡴᡡ ᠵᠠᡴᡠᠨᡳ ᡤᡳᠰᡠᠨ᠈ ᠮᡠᠰᡝ ᡝᠮᡠ ᠠᠪᠠᠮᠪᡳ

ᠪᡠᠮᠪᡳᠯᡝᠰᡝ ᡝᠮᡠ ᡤᡝᠮᡠᠨᡳ https:// URL᠈ 10 MB ᡩᡝ ᡩᡝᠷᡤᡳ data: URI ᠵᡝᡵᡤᡳ ᡝᠮᡝ᠈ ᡳᠨᡝ ᠪᡠᠮᠪᡳᠯᡝᠰᡝᠨᡳ file_url ᠠᠪᠠᠮᠪᡳ ᠪᡠᠮᠪᡳ

ᠪᡠᠶᡝᠮᡝ

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"
  }
}
ᡤᡝᠯᡝᠮᡝ ᡥᡡᠯᡤᡠᠨᡳ ᡳᠨᡠᡝᠯᡝᡥᡝ outputs[].url ᠰᡠᠯᡠᠨ ᡩᡝ ᠰᡳᡵᡝ ᡶᡳᠯᡝ᠈ ᠝ᠮᡤᡳ ᠮᡠᠰᡝ ᠠᠪᠠᠯᡳ ᠵᡝᠮᡤᡳᠨ GB-ᠪᡳᠶᠠ ᠵᡝᠮᡤᡳᠨ ᠪᡝ ᡝᠮᡠᠯᡝᠮᡝ ᠠᠪᠠᠯᡳ 7 ᡥᠠᠨ ᠰᡳᠯᡤᠠᠨ ᡩᡝ᠈ ᠰᡳᠨᡳ ᠪᠠᠯᠠᠨᠰᡳ ᠵᡠᠶᡝᡵᡝᠨ ᠠᠪᠠᠯᡳ ?storage= ᡩᡝ ᡝᠵᡝᠨ ᡥᠠᠯᠠᠮᡝ᠉
ᡝᠮᡠ ᡤᡳᠰᡠᠨ ᡝᠮᡠ ᠮᠣᡩᡝᠯ ᡩᡝtype, url, content_type, width, height ᠮᠠᠩᡤᡳ duration᠈ ᠵᠠᠯᠠᠨ᠈ ᠪᡠᠵᡠᠮᠪᡳ ᠮᠠᠩᡤᡳ ᠵᡝᡵᡤᡳ ᡩᡝᠨᡳ᠈ output ᠮᠣᡩᡝᠯᡳᠨᡳ ᡝᠮᡠ ᠵᠠᠯᠠᠨ
ᠪᡠᠶᡝᠮᡝᠨᡳ ᡤᡳᠰᡠᠨ
video
object {url, content_type, file_name, file_size}ᠪᡠᠶᡝᠮᡝᠨᡳ ᠰᡠᠨᡤᠠ ᠶᠠᠪᡠᠮᡝ ᡶᡳᠯᡝ.
duration
number

ᡝᠯᡤᡳ ᡩᠠᠯᡳᠨ: ᠠᠮᡤᠠ ᡩᡝ ᠰᡠᠨᡤᠠ

AI ᠠᡤᡝᠨᡨᡳ ᡠᠴᡠᠷᡳ᠈ ᡝᡵᡝ ᡩᡝᠪᡝᡵᡳ Markdown ᠰᡳᠨᡩᠠᡵᡳ https://doitong.com/mnc/developers/models/bytedance/omnihuman/v2.md. ᡝᡵᡝ ᠮᠣᡩᡝᠯ ᠵᠠᡴᡠᠨ ᠰᡠᠯᡠᠮᡝ https://doitong.com/developers/llms.txt