{
 "api_version": "1.0",
 "slug": "omnihuman",
 "name": "OmniHuman",
 "type": "model",
 "type_label": "Model",
 "summary": "A ByteDance model that turns one photo plus a voice or music track into a video of that person talking, singing or moving, from head-and-shoulders up to full body. Not downloadable; businesses pay per second through ByteDance's BytePlus cloud.",
 "areas": [
  {
   "id": "avatar",
   "label": "Talking presenters"
  },
  {
   "id": "video",
   "label": "Video"
  }
 ],
 "what_its_for": [
  {
   "id": "make.avatar.talking_photo",
   "label": "A talking presenter, a talking version of a photo",
   "main": true
  },
  {
   "id": "make.video.from_photo",
   "label": "A video, by bringing a photo to life",
   "main": false
  },
  {
   "id": "make.video.motion_transfer",
   "label": "A video, by copying movement from another video",
   "main": false
  }
 ],
 "inputs_outputs": [
  "audio_to_video",
  "image_to_video",
  "video_to_video"
 ],
 "openness": {
  "id": "closed",
  "label": "Closed",
  "explanation": "Only usable through the maker's app or API",
  "open_source": false
 },
 "licence": {
  "family": "proprietary",
  "family_label": "The maker's own terms",
  "name": "BytePlus service terms",
  "url": null
 },
 "commercial_use": {
  "headline": "unclear",
  "label": "The terms don't say clearly",
  "cheapest_commercial_plan": null,
  "conditions": [],
  "rights_survive_cancel": null
 },
 "cost": {
  "free_option": false,
  "free_tier": false,
  "free_tier_includes": null,
  "free_to_run_yourself": false,
  "cheapest_paid": null,
  "plans": [
   {
    "name": "OmniHuman 1.5 API",
    "price": 0.12,
    "currency": "USD",
    "period": "per_use",
    "billed": "usage",
    "price_text": "$0.12 per seconds of video",
    "includes": [
     {
      "unit": "seconds_of_video",
      "unit_label": "seconds of video",
      "quantity": 1,
      "per": null
     }
    ],
    "commercial_use": null,
    "note": null
   },
   {
    "name": "fal, OmniHuman v2",
    "price": 0.105,
    "currency": "USD",
    "period": "per_use",
    "billed": "usage",
    "price_text": "$0.105 per seconds of video",
    "includes": [
     {
      "unit": "seconds_of_video",
      "unit_label": "seconds of video",
      "quantity": 1,
      "per": "once"
     }
    ],
    "commercial_use": "yes",
    "note": null
   }
  ],
  "plans_complete": false,
  "estimates": [],
  "note": "Prices as published by the maker. Anything in estimates is Plainly's own rough comparison, not a maker price."
 },
 "access": {
  "routes": [
   {
    "id": "vendor_api",
    "label": "Maker's own API"
   }
  ],
  "platforms": [
   "web"
  ]
 },
 "skill_level": {
  "id": "technical",
  "label": "Technical"
 },
 "made_by": {
  "name": "ByteDance"
 },
 "status": {
  "id": "active",
  "label": "Available"
 },
 "rights_and_safety": {
  "trains_on_your_work": null,
  "watermark": null,
  "copies_real_faces_or_voices": [
   {
    "kind": "face",
    "route": "animate any photo via API",
    "consent": "none"
   }
  ],
  "limits": null
 },
 "related": {
  "uses_models": [],
  "uses_models_not_listed": [],
  "available_on": [
   {
    "slug": "fal",
    "name": "fal",
    "type": "host",
    "json": "https://plainly.guide/api/tools/fal.json"
   }
  ],
  "hosts_models": [],
  "replaced_by": []
 },
 "alternatives": {
  "for_task": "make.avatar.talking_photo",
  "for_task_label": "A talking presenter, a talking version of a photo",
  "entries": [
   {
    "slug": "akool",
    "name": "Akool",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/akool.json"
   },
   {
    "slug": "d-id",
    "name": "D-ID",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/d-id.json"
   },
   {
    "slug": "deevid-ai",
    "name": "DeeVid AI",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/deevid-ai.json"
   },
   {
    "slug": "domo-ai",
    "name": "DomoAI",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/domo-ai.json"
   },
   {
    "slug": "dreamina",
    "name": "Dreamina",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/dreamina.json"
   },
   {
    "slug": "dzine",
    "name": "Dzine",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/dzine.json"
   },
   {
    "slug": "echomimic",
    "name": "EchoMimic",
    "type": "model",
    "json": "https://plainly.guide/api/tools/echomimic.json"
   },
   {
    "slug": "elai-io",
    "name": "Elai.io",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/elai-io.json"
   },
   {
    "slug": "fal",
    "name": "fal",
    "type": "host",
    "json": "https://plainly.guide/api/tools/fal.json"
   },
   {
    "slug": "fantasytalking",
    "name": "FantasyTalking",
    "type": "model",
    "json": "https://plainly.guide/api/tools/fantasytalking.json"
   },
   {
    "slug": "hallo2",
    "name": "Hallo2",
    "type": "model",
    "json": "https://plainly.guide/api/tools/hallo2.json"
   },
   {
    "slug": "hedra",
    "name": "Hedra",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/hedra.json"
   },
   {
    "slug": "heygen",
    "name": "HeyGen",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/heygen.json"
   },
   {
    "slug": "hunyuanvideo-avatar",
    "name": "HunyuanVideo-Avatar",
    "type": "model",
    "json": "https://plainly.guide/api/tools/hunyuanvideo-avatar.json"
   },
   {
    "slug": "infinitetalk",
    "name": "InfiniteTalk",
    "type": "model",
    "json": "https://plainly.guide/api/tools/infinitetalk.json"
   },
   {
    "slug": "jogg-ai",
    "name": "Jogg AI",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/jogg-ai.json"
   },
   {
    "slug": "liveportrait",
    "name": "LivePortrait",
    "type": "model",
    "json": "https://plainly.guide/api/tools/liveportrait.json"
   },
   {
    "slug": "magic-hour",
    "name": "Magic Hour",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/magic-hour.json"
   },
   {
    "slug": "musetalk",
    "name": "MuseTalk",
    "type": "model",
    "json": "https://plainly.guide/api/tools/musetalk.json"
   },
   {
    "slug": "sadtalker",
    "name": "SadTalker",
    "type": "model",
    "json": "https://plainly.guide/api/tools/sadtalker.json"
   },
   {
    "slug": "veed",
    "name": "VEED",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/veed.json"
   },
   {
    "slug": "vidnoz",
    "name": "Vidnoz AI",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/vidnoz.json"
   },
   {
    "slug": "vozo",
    "name": "Vozo",
    "type": "tool",
    "json": "https://plainly.guide/api/tools/vozo.json"
   },
   {
    "slug": "wavespeed-ai",
    "name": "WaveSpeedAI",
    "type": "host",
    "json": "https://plainly.guide/api/tools/wavespeed-ai.json"
   }
  ]
 },
 "last_updated": "2026-11-07",
 "entry_status": "draft",
 "sources": [
  {
   "field": "access",
   "url": "https://www.byteplus.com/en/product/OmniHuman",
   "checked": "2026-10-12",
   "confidence": "medium",
   "confidence_label": "Checked, but the page was unclear or partial",
   "note": "Official API through BytePlus; native 1080p output. ByteDance's consumer apps may also use it but this was not checked."
  },
  {
   "field": "commercial_use",
   "url": "https://www.byteplus.com/en/product/OmniHuman",
   "checked": "2026-10-12",
   "confidence": "low",
   "confidence_label": "Inferred or from a secondary source; needs review",
   "note": "Product page sells API access to businesses but doesn't state output rights; BytePlus terms not read."
  },
  {
   "field": "licence",
   "url": "https://www.byteplus.com/en/product/OmniHuman",
   "checked": "2026-10-12",
   "confidence": "low",
   "confidence_label": "Inferred or from a secondary source; needs review",
   "note": "Terms for the BytePlus API were not read."
  },
  {
   "field": "lifecycle",
   "url": "https://www.byteplus.com/en/product/OmniHuman",
   "checked": "2026-11-07",
   "confidence": "high",
   "confidence_label": "Checked on the maker's own page",
   "note": "BytePlus page centres on version 1.5; a version 2 is offered on fal (Nov 2026)."
  },
  {
   "field": "likeness_cloning",
   "url": "https://www.byteplus.com/en/product/OmniHuman",
   "checked": "2026-10-12",
   "confidence": "low",
   "confidence_label": "Inferred or from a secondary source; needs review",
   "note": "Works from any single photo. API docs list an optional 'subject recognition' step but don't say what it checks; no consent step described."
  },
  {
   "field": "made_by",
   "url": "https://omnihuman-lab.github.io/",
   "checked": "2026-10-12",
   "confidence": "high",
   "confidence_label": "Checked on the maker's own page",
   "note": "Research page credits ByteDance Intelligent Creation; offered commercially by BytePlus. No company address read, so no country."
  },
  {
   "field": "modalities",
   "url": "https://omnihuman-lab.github.io/",
   "checked": "2026-10-12",
   "confidence": "high",
   "confidence_label": "Checked on the maker's own page",
   "note": "Always needs one reference image plus audio, video or both; v1.5 adds an optional text prompt."
  },
  {
   "field": "openness",
   "url": "https://omnihuman-lab.github.io/",
   "checked": "2026-10-12",
   "confidence": "high",
   "confidence_label": "Checked on the maker's own page",
   "note": "Research page says the team offers no downloads; no weights or code released."
  },
  {
   "field": "pricing",
   "url": "https://www.byteplus.com/en/product/OmniHuman",
   "checked": "2026-10-12",
   "confidence": "medium",
   "confidence_label": "Checked, but the page was unclear or partial",
   "note": "Two different per-second prices on the same page; confirm before budgeting. fal lists OmniHuman v2 at $0.105 per output second (checked 7 Nov 2026)."
  },
  {
   "field": "skill_level",
   "url": "https://www.byteplus.com/en/product/OmniHuman",
   "checked": "2026-10-12",
   "confidence": "medium",
   "confidence_label": "Checked, but the page was unclear or partial",
   "note": "Our judgement: API only from the maker."
  },
  {
   "field": "tasks",
   "url": "https://omnihuman-lab.github.io/",
   "checked": "2026-10-12",
   "confidence": "high",
   "confidence_label": "Checked on the maker's own page",
   "note": "Driven mainly by audio (speech or singing); can also copy movement from a reference video. Works on cartoons and animals too."
  }
 ],
 "links": {
  "page": "https://plainly.guide/tools/omnihuman/",
  "website": "https://omnihuman-lab.github.io/",
  "affiliate": null,
  "translations": {
   "es": "https://plainly.guide/es/tools/omnihuman/",
   "fr": "https://plainly.guide/fr/tools/omnihuman/"
  }
 },
 "attribution": "Data from Plainly Guide (https://plainly.guide). Please credit Plainly with a link to the entry page when you use it."
}