{
 "slug": "voca",
 "name": "VOCA (Voice Operated Character Animation)",
 "author": "Max Planck Institute for Intelligent Systems",
 "density": "full",
 "status": "active",
 "status_note": null,
 "alternatives_page": null,
 "one_liner": "Speech-driven 3D facial animation model with code; data and trained model need a free sign-in.",
 "category": {
  "slug": "ai-presenters",
  "name": "AI presenters and avatars"
 },
 "tags": [
  "Open source"
 ],
 "styles": [],
 "logo_url": "https://agentgid.com/media/avatars/timobolkart.png",
 "logo_letter": "V",
 "links": {
  "repo": "https://github.com/TimoBolkart/voca",
  "website": null,
  "api_docs": null
 },
 "preview": null,
 "verdicts": [
  {
   "key": "price",
   "label": "Price",
   "value": "Free",
   "status": "yes",
   "sub": "No paid plan",
   "quote": null,
   "note": "Free of charge for non-commercial research, education and artistic projects.",
   "source": {
    "label": "github.com/TimoBolkart/voca",
    "url": "https://github.com/TimoBolkart/voca"
   },
   "n": 1
  },
  {
   "key": "commercial",
   "label": "Commercial use",
   "value": "No",
   "status": "no",
   "sub": "Max Planck non-commercial…",
   "quote": "Any other use, in particular any use for commercial purposes, is prohibited.",
   "note": "Any commercial use, including a commercial product or service, is forbidden without a separate license.",
   "source": {
    "label": "voca.is.tue.mpg.de/license.html",
    "url": "https://voca.is.tue.mpg.de/license.html"
   },
   "n": 2
  },
  {
   "key": "credit",
   "label": "Credit the author",
   "value": "Not checked yet",
   "status": "unknown",
   "sub": null,
   "quote": null,
   "note": null,
   "source": {
    "label": "voca.is.tue.mpg.de/license.html",
    "url": "https://voca.is.tue.mpg.de/license.html"
   },
   "n": 3
  },
  {
   "key": "agent_access",
   "label": "Agent access",
   "value": "Download",
   "status": "info",
   "sub": "Files by hand",
   "quote": null,
   "note": "There is no package or API. Files are downloaded by hand from the official site.",
   "source": {
    "label": "github.com/TimoBolkart/voca",
    "url": "https://github.com/TimoBolkart/voca"
   },
   "n": 4
  }
 ],
 "license": {
  "name": "Max Planck non-commercial research license",
  "url": "https://voca.is.tue.mpg.de/license.html",
  "summary": "Free only for non-commercial research, teaching and art projects. Paid products, paid services, sharing the files with others and pornographic use are not allowed; commercial use needs a separate deal with Max Planck.",
  "pages_read": 1,
  "rules": [
   "Non-commercial research, education and artistic projects only.",
   "No redistribution of the data or software; no use in commercial services.",
   "Do not use it for pornographic material."
  ],
  "rows": [
   {
    "label": "Commercial use",
    "value": "No",
    "status": "no",
    "quote": "Any other use, in particular any use for commercial purposes, is prohibited.",
    "source": {
     "label": "voca.is.tue.mpg.de/license.html",
     "url": "https://voca.is.tue.mpg.de/license.html"
    },
    "note": null
   },
   {
    "label": "Credit",
    "value": "Not stated",
    "status": "unknown",
    "quote": null,
    "source": null,
    "note": null
   },
   {
    "label": "Inside your app or game",
    "value": "Not allowed",
    "status": "no",
    "quote": "incorporation in a commercial product, use in a commercial service, or production of other artefacts for commercial purposes.",
    "source": {
     "label": "voca.is.tue.mpg.de/license.html",
     "url": "https://voca.is.tue.mpg.de/license.html"
    },
    "note": null
   },
   {
    "label": "Pass the files on to your users",
    "value": "Not allowed",
    "status": "no",
    "quote": "The Data and Software and the license herein granted shall not be copied, shared, distributed, re-sold, offered for re-sale, transferred or sub-licensed in whole or in part except that you may make one copy for archive purposes only.",
    "source": {
     "label": "voca.is.tue.mpg.de/license.html",
     "url": "https://voca.is.tue.mpg.de/license.html"
    },
    "note": "Sharing, reselling or sublicensing is forbidden; one archive copy is allowed."
   },
   {
    "label": "Monetized YouTube",
    "value": "Not stated",
    "status": "unknown",
    "quote": "Any other use, in particular any use for commercial purposes, is prohibited.",
    "source": {
     "label": "voca.is.tue.mpg.de/license.html",
     "url": "https://voca.is.tue.mpg.de/license.html"
    },
    "note": null
   },
   {
    "label": "AI training",
    "value": "Banned by the terms",
    "status": "no",
    "quote": "This license also prohibits the use of the Data and Software to train methods/algorithms/neural networks/etc. for commercial use of any kind.",
    "source": {
     "label": "voca.is.tue.mpg.de/license.html",
     "url": "https://voca.is.tue.mpg.de/license.html"
    },
    "note": null
   },
   {
    "label": "Bots and bulk downloads",
    "value": "Not stated",
    "status": "unknown",
    "quote": null,
    "source": null,
    "note": null
   }
  ],
  "checked_at": "2026-10-27",
  "commercial_use_page": "https://agentgid.com/assets/voca/commercial-use/"
 },
 "overview": {
  "heading": "VOCA: a 3D face that talks along with a voice",
  "body": "VOCA is a research model from the Max Planck Institute that moves a 3D head model's lips, jaw and face to match any speech recording. You give it a sound file and a still 3D face, and it returns an animation you can render to video. It is free only for non-commercial research, teaching and art, and the model files need a free sign-up."
 },
 "uses": [
  {
   "title": "A talking 3D head from a voice clip",
   "text": "Record or pick a speech clip and let VOCA move a 3D face to it. You get a short video and the face shapes for every frame.",
   "idea": false,
   "image": null
  },
  {
   "title": "Lip-sync for game and VR characters",
   "text": "Animate a character's face for a game scene or a virtual reality avatar when you do not know the speaker or language in advance. This fits non-commercial and art projects only.",
   "idea": false,
   "image": null
  },
  {
   "title": "Add blinks and head turns",
   "text": "After the speech animation is done, add eye blinks, change the face shape or turn the head, so the result looks less stiff.",
   "idea": false,
   "image": null
  },
  {
   "title": "New faces to animate",
   "text": "Make random new heads to try the same speech on different faces, or build a head from a photo with the related RingNet project.",
   "idea": false,
   "image": null
  },
  {
   "title": "A class project on talking faces",
   "text": "Students can compare how speaking styles change the same sentence, using the ready style switch, in a course or thesis.",
   "idea": true,
   "image": null
  },
  {
   "title": "Animated preview for a short art film",
   "text": "Give a sculpted or scanned head a voice for a non-commercial short film or gallery piece, then render it in your own tool.",
   "idea": true,
   "image": null
  }
 ],
 "start": {
  "prompt": "Set up VOCA from github.com/TimoBolkart/voca in a Python 3.6 or 3.7 virtual environment with the pinned TensorFlow 1.x requirements, wait for me to download the model and FLAME files after I sign up, then run run_voca.py on my wav file with --visualize False and keep it to my non-commercial project.",
  "install": null,
  "install_note": null,
  "code": [
   {
    "tab": "Step 1",
    "intro": "Make a Python virtual environment (the code was tested on Python 3.6.8 and TensorFlow 1.14), install FFmpeg and the MPI-IS mesh library, then the requirements.",
    "source": "git clone https://github.com/TimoBolkart/voca.git\npip install -r requirements.txt"
   },
   {
    "tab": "Step 2",
    "intro": "The person signs up on the VOCA and FLAME sites and accepts both licenses; then the fetch script downloads the model, the FLAME head model and the DeepSpeech files.",
    "source": "./fetch_data.sh"
   },
   {
    "tab": "Step 3",
    "intro": "Run the demo on the sample sentence and the sample head.",
    "source": "python run_voca.py --tf_model_fname './model/gstep_52280.model' --ds_fname './ds_graph/output_graph.pb' --audio_fname './audio/test_sentence.wav' --template_fname './template/FLAME_sample.ply' --condition_idx 3 --out_path './animation_output'"
   }
  ]
 },
 "mistakes": [
  {
   "dont": "Install it on a current Python with the latest TensorFlow 2",
   "fix": "Use an old Python (3.6 or 3.7) virtual environment and the pinned TensorFlow 1.x from requirements.txt",
   "why": "The code was written and tested for TensorFlow 1.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "pip install psbody-mesh from PyPI, or skip it",
   "fix": "Build the mesh library from github.com/MPI-IS/mesh inside the same virtual environment",
   "why": "Without it the run stops with ModuleNotFoundError No module named 'psbody'.",
   "dont_code": true,
   "fix_code": false
  },
  {
   "dont": "Run the demo on a remote server with the default video rendering",
   "fix": "Add --visualize False and render the saved face shapes later with another tool",
   "why": "The default renderer breaks on some setups, such as remote machines.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "The agent types the person's VOCA and FLAME username and password into fetch_data.sh",
   "fix": "The person runs fetch_data.sh, or downloads the files from the two sites by hand",
   "why": "The script asks for the person's own account login for each site.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "Pass any 3D head file, such as a game character, as --template_fname",
   "fix": "Use a head in FLAME topology (fitted to a scan or image, or sampled with sample_templates.py)",
   "why": "VOCA can only animate heads that share FLAME's structure.",
   "dont_code": false,
   "fix_code": false
  }
 ],
 "agent": {
  "self_serve": false,
  "self_serve_text": null,
  "install": null,
  "repo": "https://github.com/TimoBolkart/voca",
  "api_docs": null,
  "api_account": "Not needed. Everything runs on your side.",
  "get_files": null,
  "formats": [],
  "limits": null,
  "mcp": null,
  "mcp_url": null,
  "credit_line": "Animation made with VOCA (Max Planck Institute for Intelligent Systems), voca.is.tue.mpg.de, for non-commercial research",
  "rules_text": "- VOCA (Voice Operated Character Animation) (AI presenters and avatars). Speech-driven 3D facial animation model with code; data and trained model need a free sign-in. Price: free; non-commercial only; cannot ship inside an app; no AI training on its content.\n  Connect: download from https://github.com/TimoBolkart/voca (no API).\n  Rule: Non-commercial research, education and artistic projects only.\n  Rule: No redistribution of the data or software; no use in commercial services.\n  Rule: Do not use it for pornographic material.\n  License: https://voca.is.tue.mpg.de/license.html (checked 2026-10-27; details: https://agentgid.com/assets/voca/)",
  "agent_md": "https://agentgid.com/assets/voca/agent.md",
  "card_json": "https://agentgid.com/assets/voca/card.json"
 },
 "popularity": {
  "gid_score": 10,
  "stars": 1271,
  "downloads_7d": null,
  "downloads_7d_label": null,
  "downloads_change_4w_pct": null,
  "eco": null,
  "package": null,
  "repo": "TimoBolkart/voca",
  "agent_projects": null,
  "agent_projects_total": null,
  "downloads_unconfirmed": false,
  "series": {
   "downloads_weekly": [],
   "stars": [
    [
     "2026-11-07",
     1272
    ],
    [
     "2026-11-08",
     1272
    ],
    [
     "2026-11-09",
     1272
    ],
    [
     "2026-11-10",
     1272
    ],
    [
     "2026-11-11",
     1272
    ],
    [
     "2026-11-12",
     1271
    ],
    [
     "2026-11-13",
     1271
    ],
    [
     "2026-11-14",
     1271
    ],
    [
     "2026-11-15",
     1271
    ],
    [
     "2026-11-16",
     1271
    ],
    [
     "2026-11-17",
     1271
    ],
    [
     "2026-11-18",
     1271
    ],
    [
     "2026-11-19",
     1271
    ]
   ]
  },
  "stars_flat_since": null,
  "updated_at": "2026-11-19"
 },
 "alternatives": [
  {
   "slug": "voca",
   "name": "VOCA (Voice Operated Character Animation)",
   "why": null,
   "current": true,
   "price": "Free",
   "commercial": {
    "value": "Non-commercial",
    "status": "no"
   },
   "access": "Download"
  },
  {
   "slug": "liveportrait",
   "name": "LivePortrait",
   "why": "Pick LivePortrait when you want to animate a portrait photo from a driving video, not a 3D head from sound.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "Download"
  },
  {
   "slug": "soulx-flashtalk",
   "name": "SoulX-FlashTalk",
   "why": "Pick SoulX-FlashTalk when you need a talking-avatar video made from an image and a voice, not 3D face shapes.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "Commercial OK",
    "status": "yes"
   },
   "access": "Download"
  },
  {
   "slug": "heygen",
   "name": "HeyGen",
   "why": "Pick HeyGen when the talking presenter video is for a business and you are fine paying a hosted service.",
   "current": false,
   "price": "Free tier",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "MCP, API, npm"
  },
  {
   "slug": "synthesia",
   "name": "Synthesia",
   "why": "AI avatar video platform with an API and MCP; free videos carry a watermark.",
   "current": false,
   "price": "Free tier",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "MCP, API"
  },
  {
   "slug": "vidyard",
   "name": "Vidyard",
   "why": "Video hosting and messaging platform with AI avatar presenters, personalized video generation and analytics for sales teams.",
   "current": false,
   "price": "Free tier",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "MCP"
  }
 ],
 "faq": [
  {
   "q": "Can I use VOCA for a paid app, a client job or a monetised video?",
   "a": "No. The license allows only non-commercial research, teaching and art; commercial use needs a separate license from Max Planck."
  },
  {
   "q": "Does it work with speech that is not in English?",
   "a": "Yes, the project page says it takes any speech, including other languages."
  },
  {
   "q": "Can I animate my own 3D character with it?",
   "a": "Only a head in FLAME topology. You can make one by fitting FLAME to a scan or an image, or by sampling random FLAME heads."
  },
  {
   "q": "Can I change how the person speaks or moves the head?",
   "a": "Yes. VOCA has controls for speaking style, face shape and head, jaw and eye rotation."
  },
  {
   "q": "Can I share the model files with my team or put them in my project download?",
   "a": "No. Each person gets the license personally, and the files may not be shared, except one archive copy."
  }
 ],
 "at_a_glance": {
  "latest_version": "master (last push 2024-08-20)",
  "last_commit": "2024-08-20",
  "runtime": "Python 3.6.8 and TensorFlow 1.14 as tested (requirements.txt pins tensorflow-gpu 1.15.2), FFmpeg, the MPI-IS mesh library; the trained model and FLAME files from the sign-up sites.",
  "key_needed": false
 },
 "good_to_know": [
  "The trained model, sample sounds and head files are not in the code download. You need a free account on the VOCA site and a second one on the FLAME site.",
  "The code is old. It was tested on Python 3.6.8 and TensorFlow 1.14, and its package list pins TensorFlow 1.15.2 for graphics cards.",
  "The FLAME head model it needs has its own non-commercial license, which also bans fake, misleading or defamatory content.",
  "The added eye blink is only a demonstration of moving the eyelids, not a natural blink.",
  "If you publish work that uses VOCA, the license asks you to cite its research paper."
 ],
 "stack_snippets": [],
 "claims": [
  "VOCASET has about 29 minutes of 4D scans at 60 fps with audio from 12 speakers"
 ],
 "checked": {
  "license_read": "2026-10-27",
  "overview_checked": "2026-11-19",
  "numbers_updated": "2026-11-19",
  "sources": [
   {
    "label": "github.com/TimoBolkart/voca",
    "url": "https://github.com/TimoBolkart/voca"
   },
   {
    "label": "README on GitHub",
    "url": "https://github.com/TimoBolkart/voca/blob/master/README.md"
   },
   {
    "label": "github.com/TimoBolkart/voca/blob/master/requirements.txt",
    "url": "https://github.com/TimoBolkart/voca/blob/master/requirements.txt"
   },
   {
    "label": "github.com/TimoBolkart/voca/blob/master/fetch_data.sh",
    "url": "https://github.com/TimoBolkart/voca/blob/master/fetch_data.sh"
   },
   {
    "label": "voca.is.tue.mpg.de",
    "url": "https://voca.is.tue.mpg.de/"
   },
   {
    "label": "voca.is.tue.mpg.de/license.html",
    "url": "https://voca.is.tue.mpg.de/license.html"
   },
   {
    "label": "flame.is.tue.mpg.de/modellicense.html",
    "url": "https://flame.is.tue.mpg.de/modellicense.html"
   }
  ],
  "unverified": null
 },
 "user_reports": null,
 "url": "https://agentgid.com/assets/voca/",
 "note": "Written by AgentGid from the official pages in checked.sources; quotes are copied from those pages. status: yes | cond | no | unknown | info. Prices and vendor claims are as reported on the checked date. Not legal advice."
}
