This page is a roadmap for upcoming features and releases. While we can't guarantee that releases will happen on a particular
day, some rough dates have been provided where possible.
The following items are the most set in stone and may have definite dates.
LipSync Lite 1.5 - May 2019
Update for LipSync Lite, bringing it back to the Asset Store and in-line with version 1.5 of LipSync Pro.
Documentation Update - Throughout May & June 2019
Additional pages documenting new AutoSync features, editor windows and updates to existing pages.
Marker Cleanup Module Update - June 2019
Update to the Marker Cleanup Module that will allow smarter discarding of markers including filtering based on phoneme, and
re-timing of markers to more evenly fill gaps left behind.
Intensity from Volume Module Update - June 2019
Update to the Set Intensity from Volume module that will add filtering options and a better workflow for defining the minimum &
maximum marker intensities and how they relate to the audio volume.
Google Cloud Transcription Module - July 2019
The first of the online cloud-based modules. This will allow linking to a Google Cloud account (must be set-up manually) and
getting a transcript of your audio automatically for use with the MFA module or similar. Note: This will require a 3rd-party
account and may incur costs based on usage. Make sure you understand Google Cloud Speech-to-Text pricing structure before use.
These items may have longer timescales or be difficult to predict when they'll be ready.
New Montreal Forced Aligner Language Models - Q3 2019 and beyond
Adding support for some other languages to the MFA module. This will include Presets, Phoneme Maps and, where applicable,
alternative Phoneme Sets, tailored to get the best results. We can't say for sure which languages will be available or when,
but the most likely ones will be Mandarin Chinese, French, German, Russian, or Spanish.
Other Cloud-based Modules - Q3 2019 and beyond
Similar to the Google Cloud Module, offering online transcription using other cloud services such as Microsoft Azure or IBM Watson.
Watson specifically may also bring an experimental Emotion Detection Module, using their AI sentiment analysis service to
markup a transcript with likely emotions, map those to LipSync Pro emotions present in the project and then use an aligner (e.g. MFA)
to time the resultant emotion markers.
Similarly, these can incur pay-as-you-go charges or require subscriptions depending on the service owners.
LipSync Pro 2.0 - 2020
LipSync Pro 2.0 is an entirely new product, built from the ground up to include all the functionality of the current version 1.x while
making use of Unity's newest features, including DOTS, the Playables API and UIElements.
This is a long-term project and it shouldn't be expected to release before these Unity engine features are deemed production-ready.
The plan is that this new iteration of LipSync Pro will form part of a new facial & cinematic animation suite. More information will
follow later in the year, but rest assured LipSync Pro will remain supported and up-to-date with Unity into the new decade.