High-Quality & Cost-Effective

Speech Graphics technology re-creates the physical motions of speech, resulting in natural and believable facial animation with perfect lip sync. Our procedural solution eliminates the need for hand animation or motion capture, saving money and time. Using audio alone gives you greater flexibility to iterate, meet deadlines, and re-animate in different languages.

Our solution flows into your pipeline

All facial animation projects begin with a secure asset transfer. Speech Graphics can accept facial models in any format (.fbx, .ma, .max, etc.). From there, Speech Graphics performs a setup step to map our advanced tech to your facial rig. Once the model is set up in our system, we are ready for production.

In order to get the highest quality animations, .wav or other uncompressed audio format is preferred, but we can work with any audio format.

As lines of dialogue are received from your studio, an input check is performed to ensure an exact match between each audio file and its transcript. The verified input is then processed through the Speech Graphics animation system.

After the audio is processed, each output animation is examined by our experts, and the analysis is edited to correct any errors.

The final tuned output goes back to your studio as facial animation key frames on the rig.

You’re in good company

Centroid motion capture logo
Audiomotion logo
Prettybird logo
Saundz Logo
The University of Edinburgh's logo
Mimic Productions logo