'Really Great' Lipsync!
Annosoft is the leading provider of automatic lipsync technologies for game and multimedia development. Our customers include some of the biggest names in the game industry.
Our Lipsync SDKs are used in big games such as Red Faction: Guerilla, Saint's Row 2, Infamous, Fable 2, Rage, Harry Potter and the Half-Blood Prince...and in many of yesterday's hit games.
Save time, money, and aggrevation while improving the quality of your game.
Localization? Automate NPC animation using proven technology and techniques. Late cycle? The Lipsync SDKs shave time off your schedule, at the beginning or near the end, without changing your engine.
Product Review - April 2006 Game Developer Magazine (pdf)
New - XBox 360™ Support in the Realtime Lipsync SDK
Annosoft products can be relied on to build high-quality mouth animations without manual work. Whether you have 10, or 1000, or 100,000 audio files to lip sync, our products can get it done, quickly and accurately.
Not all lipsync tools and technologies are equal. Our technologies are the highest quality, most flexible, and best performing lipsync technologies available.
Annosoft developed this speech software for this problem. It isn't an "afterthought" market and we aren't reselling someone else's software. Other vendors cannot say this. Our software does it's job well and we can support every aspect of the software without having to refer to 3rd parties. This is a critical feature for customers with tight deadlines.
The evaluation SDKs and evaluation products are provided at no cost.
The Lipsync Tool Demo is a good place to start your evaluation. Contact us when you are ready to go deeper.
Products
- C++ SDKs and an ActiveX Control that are easily integrated into your production process.
- Batch tools (included with the SDKs) for big jobs.
Source code included. - Desktop application for visually editing and saving lipsync results.
Technology
Our core technologies are lightweight, high performance, speech recognition engines. Using Hidden Markov Models, these technologies determine the statistically-best phonetical breakdown for a given audio file. The text-based technology, in addition to producing a precise phonetical breakdown, also produces an accurate breakdown of word positions in an audio file.
Our technologies work effectively across most, if not all, languages.
Licensing
Licensing for all our products is painless and flexible. We provide free upgrades on all our products for one year.
None of our products require royalties.
We have a downloadable demo SDK with example C++ source code available upon request.