Jump to content
Sign in to follow this  

SAPI phoneme data

Recommended Posts


Is there a way to grab the phoneme data for a line of text? For example,

D @ 0 k w I k b r aU n f Q k s dZ V m p t @U 1 v @ D @ 0 l eI 1 z i: 0 d Q g 1

is this:

The quick brown fox jumped over the lazy dog.

I'd like to input a string and get a phoneme string in return.

What I'd like to do is have a talking head lipsync to entered text. I can do the animation, the 3D and the rest, but SAPI stuff is new to me. The idea would be to create animations for phonemes, queue the animation sequence according to the phoneme setup, and then fire both events, so that the head would appear to be speaking synced with the speech data.

Any help would be appreciated!

Share this post

Link to post
Share on other sites

It looks like this is pretty much done, and the phoneme to mouth position relationship is encoded in Visemes. Which are helpfully denoted and automated by the SAPI already.


Progandy has a wonderful little script here that more than meets my needs. Thanks for any searching or interest, I think that the script was it though :)

For search reference:

Viseme, Phoneme, Animation, Lip-Sync Synching Speech TTS Text to Speech.

       ae, ax, ah
       ey, eh, uh
       y, iy, ih, ix
       w, uw
       s, z
       sh, ch, jh, zh
       th, dh
       f, v
       d, t, n
       k, g, ng
       p, b, m
Edited by JRowe

Share this post

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
Sign in to follow this