lipsyn.cc vs MakeItTalk

lipsyn.cc turns video, portraits, or illustrated characters and audio into lip-synced video online. Users can upload audio or generate speech; the homepage advertises 91 languages and 10 voices. A free five-second preview is available without signup or a card. Full-length exports are available up to Full HD (1080p), and commercial use is included with exports. Videos can include up to three characters, with uploads up to 512 MB and audio and video up to 120 minutes. Paid minute packs are prepaid and do not expire: five minutes for €6.99, 10 for €13.90, 30 for €40.50, 60 for €79.20, or 180 for €232.20. The service has a web interface, an API, and an Adobe Express plugin. API renders run asynchronously and are delivered by webhook or polling, with cURL, Python, and Node.js examples. API limits include 60 requests per minute per key and five concurrent videos per account. The site says content remains the user's and is not used for training or other purposes; it also states that the service follows GDPR and Austrian data protection laws. Completed generations and minute-pack purchases are not refundable.

MakeItTalk is Linux, self-hosted software that creates expressive talking-head videos from one facial image and an audio track. Audio content drives lip movement and nearby facial motion, while speaker information influences expressions and other talking-head movement. The project describes use with human portraits, paintings, sketches, 2D cartoons, manga, and stylized caricatures, including faces or characters not seen during training. Its repository includes pretrained models, module training code, and Google Colab demos for natural faces. For human faces and paintings, the README calls for a centered 256×256 JPG portrait and a WAV file. Optional command-line settings adjust lip motion on the x and y axes and head-motion displacement. Local setup specifies Python 3.6, ffmpeg, and Python packages; cartoon face warping on Ubuntu also requires winehq-stable. Custom puppets are listed as a to-do item, and training sections for voice conversion, the speaker-aware branch, and image-to-image translation are marked unfinished. It is free open-source research code under CC BY-NC 4.0, allowing noncommercial use under that license.