yum
gumroad
TaSTT (modular avatar)
🕑 Added 2024-03-03 07:34:03 +0000 UTC.unitypackage with modular avatar prefab
This is an OSC speech-to-text chatbox that you can attach to your avatar with modular avatar.
You will need the corresponding free OSC app (download). This app transcribes your voice locally using an optimized version of OpenAI's Whisper algorithm, then sends the transcript into VRChat with OSC.
Features:
- Extremely low avatar performance impact - 1 material slot, 12 triangles, and as little as 300 KB of texture memory (default is 5.33MB).
- Readable in mirrors. The shader detects when it's in a mirror and flips the text.
- World space lock: chatbox locks in world space when spawned (default) or when done speaking.
- Adjustable size via radial control in game.
- Phonemes: chatbox makes noise when you speak (optional, off by default).
- Text filters: lowercase, uppercase, uwu, profanity.
- Decent accuracy and latency. Cloud-based solutions like TTS Voice Wizard are better, but you have to pay to use them. Expect 1-5 seconds of latency when using this in game.
- Fast transcription in 100 languages (speak language X, get transcript in language X). This is a native Whisper feature.
- Slow translation into 200 languages (speak language X, get transcript in language Y). This is done by feeding Whisper's transcripts into Meta's NLLB translation algorithm.
- Free as in beer.
- Open source under MIT license (github).
Requirements:
- PCVR (no Quest compatibility)
- Modular avatar
- NVIDIA GPU
- Tested on 1000-4000 series GPUs.
- 2.2GB of disk space
- 900MB: CUDNN
- 470MB: transcription models
- 430MB: python environment
- 320MB: git (required to acquire python dependencies at runtime)
- 2GB of memory
- 2GB of VRAM
Avatar performance:
- Material slots: 1
- Polygons: 12
- Sync parameters: 108 bits
- 80 bits: used to send 10 characters at a time (8 bits each)
- 8 bits: active region selection
- 8 bits: chatbox scale (optional)
- 6 bits: in-game phonemes (optional)
- 1 bit: ellipsis animation (optional)
- 1 bit: enable/disable character animations (required for robustness)
- 1 bit: instantly clear board
- 1 bit: toggle on/off
- 1 bit: lock board in world space
- 1 bit: dummy parameter (tech debt; required now but will be removed in a later release)
- Texture memory: 5.33 MB
- May be lowered by reducing the font texture's resolution. The default is 2k; I recommend going as low as 512x512.
- Audio sources: 5
- Optional. Delete them if you don't want them, it won't break anything.
Strawman FAQ:
- Why does this exist? To provide a baseline STT service for everyone.
- Why is it free? Because it can be, and because speech shouldn't be paywalled.
- Why should I use it instead of cloud options? I resent having 10 million subscriptions and don't want yet another one. That's why I use this instead of cloud options.
- Does it lag me? When it's actively transcribing, it does reduce your framerate. You can use smaller models to get better performance at the cost of accuracy.
- Are there other projects doing STT? Yes, see the README on github.
- How does the chatbox only have 12 polygons? I'm using a technique called raymarching to simulate more complicated geometry inside of a box (6 faces = 12 triangles). The raymarching implementation is heavily optimized and should not lag anyone.
Legal:
- This asset, as well as the OSC app, is licensed under the MIT license. Commercial use is allowed as long as a copy of the license is provided with any copies of the asset. The provided .unitypackage includes the LICENSE file, so there's nothing to worry about when using it.
Old versions
Here is a 51-second overview of the setup process in Unity:
TaSTT (modular avatar) setup overviewThe process is described in greater detail below.
To get a test avatar:
Enable Modular Avatar using the VRC Creator Companion.
Import the TaSTT .unitypackage
Drag yum_food/TaSTT_Modular/TaSTT.prefab onto your avatar hierarchy. DO NOT put it in your armature! Place it next to your meshes as shown in the video.
Set the parent constraint on TaSTT/Container to either your dominant hand (I use my right hand) or your head.
Fine tune the position of TaSTT/Container/TaSTT by dragging and rotating it.
Build and test.
Download the latest version of the OSC app (direct link). Extract the .zip and double click TaSTT.exe. You might get a security warning. Just hit
more optionsthenrun anyway.Why does the security warning come up? Because my code is not signed. Getting a code signing cert is expensive. If you're uneasy, run your antivirus of choice before executing.
Hit
list input devices. Identify the number associated with your microphone, then select it in theMicrophonedropdown.The first time you press this button, the app will acquire all its runtime Python dependencies. Please be patient, it could take a while. It will only have to do this once.
If you're using an index or a bigscreen beyond, you can just select
indexorbeyond.
Set
Characters per syncto 10.Set
Text box rowsto 4.Set
Text box columnsto 40.Deselect
Use built-in chatbox.If you're on a 1000 series NVIDIA GPU, set
GPU compute typetofloat32.Hit
Begin transcribing. You should see your speech being transcribed in the OSC app.Press ctrl+alt+x to make the chatbox appear in game. You should see your speech show up on the box.
This is how my OSC app is configured to use the custom chatbox on a 3000 series GPU:
To upload your avatar:
In the OSC app, go to
Debugthen hitClear OSC configs.Why is this necessary? Your avatar has a bunch of parameters. OSC needs to know what parameters your avatar has. VRChat generates a file telling OSC what parameters your avatar exposes. For some reason, VRChat generates the config once then never updates it, even if you change your parameters. Deleting OSC configs forces VRChat to regenerate the config when you upload.
What does this do? It deletes AppData/LocalLow/VRChat/vrchat/OSC.
Is it safe? Yes. This does not affect any already-uploaded avatars. It'll just force the VRC SDK to generate new OSC configs whenever you upload.
Upload.
If you need further assistance, please check my discord server. There's some common troubleshooting info #debug-shortlist. Further help requests should be posted in #help.
