Voice SDK - Wit.ai General Questions Thread

[mouse_bear]

Do you have any general questions regarding the wit.ai framework within the Voice SDK? Drop your questions, concerns, and feedback here!

[CoryMDX]

I'm developing a Unity multiplayer (Photon) lobby in which I added the OpenAI API to talk to, since the Photon SDK and Meta Voice SDK scripts fight for the microphone usage, I was wondering if there was a way to inject the audio stream generated by Photon into the "App dictation experience" script. 

[CoryMDX]

I'm not sure if its the same issue but I had a somewhat similar problem where I had 2 microphone inputs and Unity would recognize a faulty microphone input as the first and main input instead of the actual working microphone, maybe something similar could be happening in the build? It would be good to have a debug UI to view which microphone input its using.

[marcoliga97]

is there a way to keep listening for commands continuously?

[joost.vrbeelding]

I am trying to understand the dictation SDK, but when I build and run the Dictation Sample scene it gives the following build error:

An asset is marked with HideFlags.DontSave but is included in the build:
Asset: 'Packages/com.meta.xr.sdk.voice/Lib/Wit.ai/Resources/witai.png'
Asset name: witai
(You are probably referencing internal Unity data in your build.)
UnityEngine.GUIUtility:ProcessEvent (int,intptr,bool&)

What is going wrong here? Is this a bug in the wit.ai package?

[jd.scogin]

I am using unity and the Wit.ai TTS. I have it working, but I can't figure out how to change the voice via script. I can change it manually but I need to be able to select a voice at run time.

Thanks Jc

[SirLuicelot]

Normally what it fixes for me is restart the editor fresh and build but no build and run, then build and run after you build, weird behavior but it works... for some reason...

[sanket.jadhav4808]

Hi There, Did you get any solution for offline-support in voice sdk as I have implemented VoiceSDK TTS but its working online and in the docs they say by using Preloading TTS Files can use it offline but theres no implementation for Preloading TTS Files on internet , I searched everywhere how to implement the offline Preloading TTS as per docs..

[ap664]

Hi,

Has anyone encountered "[VSDK ERROR] [TTSWit] Web Stream Error" after calling TTSSpeaker.Speak() for strings of a certain size? 

Around ~200 characters or so, it begins giving this error. Shorter strings are working as expected. 

Was wondering if this is by design, and/or ways to mitigate this, because it seems like a pretty low cut-off point. Thanks!

[Ayfel]

We are getting the exact same issue, wondering on this as well.

[ap664]

I learned there's a limit on length of dictation string. It seems to be around 200-250 characters. My solution is to break up the text, then use a method in Voice SDK to queue up multiple dictations. That method is TTSSpeaker.SpeakQueued(); 

The major downside here is splitting the dictation clips causes the voice to sound unnatural at the transition, since it doesn't know one clip is a continuation of the other.