Releases: I5UCC/VRCTextboxSTT
v1.4.3
🢃 Download Release
Discord Support Server
Discord Support ServerWith default settings, this program has following requirements:
- Visual C++ Redistributables
- SteamVR (IF ran in VR, no Oculus/Meta support as of now.)
- Inference on GPU (Recommended):
- CUDA enabled GPU (NVIDIA ONLY), otherwise it will fall back to using CPU.
- ~5GB of storage space.
- ~1GB of available RAM.
- ~500MB of available VRAM.
- Inference on CPU:
- ~2GB of storage space.
- ~400MB of available RAM.
Depending on settings changed in the program those requirements can change rapidly.
v1.4.3 Changelog
- Checking for updates is now done without command line windows popping up every time.
- Update progress is now shown in the program.
- Some Requirements are locked to certain versions, to prevent big updates of dependencies to break the program.
- A few background fixes for the development side of things.
Full Changelog: v1.4.1...v1.4.3
Installing and Updating TextboxSTT
Install the Visual C++ Redistributables
After first launch, the TextboxSTT Launcher will tell you that the program is not yet installed and asks you if you want to only install the CPU dependencies:
After selecting an option (y = yes, n = no), No by default and recommended, TextboxSTT will start installing all the dependencies needed. This only has to be done once, after it will update dependencies whenever an update is available.
After the installation is done, TextboxSTT will start like normal.
To know whether an update is available, a button in the top right of the program will appear, informing you of a new update:
After clicking this button, the program will be updated and leads to a restart of the program. This process generally doesnt take much time.
v1.4.2
🢃 Download Release
Discord Support Server
With default settings, this program has following requirements:
- Visual C++ Redistributables
- SteamVR (IF ran in VR, no Oculus/Meta support as of now.)
- Inference on GPU (Recommended):
- CUDA enabled GPU (NVIDIA ONLY), otherwise it will fall back to using CPU.
- ~5GB of storage space.
- ~1GB of available RAM.
- ~500MB of available VRAM.
- Inference on CPU:
- ~2GB of storage space.
- ~400MB of available RAM.
Depending on settings changed in the program those requirements can change rapidly.
v1.4.2 Changelog
- change some default config settings
- mode is set to "once_continuous" by default now.
- SteamVR Overlay enabled by default now.
- Fixed setting VAD in the UI not saving.
Known issues updating to this version from v1.3.x:
- Your custom bindings might have been reset and TextboxSTT might show up twice in the steamVR legacy binding UI.
To fix this, youll have to redo your bindings for the newly added version.
Full Changelog: v1.4.1...v1.4.2
Installing and Updating TextboxSTT
Install the Visual C++ Redistributables
After first launch, the TextboxSTT Launcher will tell you that the program is not yet installed and asks you if you want to only install the CPU dependencies:
After selecting an option (y = yes, n = no), No by default and recommended, TextboxSTT will start installing all the dependencies needed. This only has to be done once, after it will update dependencies whenever an update is available.
After the installation is done, TextboxSTT will start like normal.
To know whether an update is available, a button in the top right of the program will appear, informing you of a new update:
After clicking this button, the program will be updated and leads to a restart of the program. This process generally doesnt take much time.
v1.4.1 portable git
🢃 Download Release
Discord Support Server
With default settings, this program has following requirements:
- Visual C++ Redistributables
- SteamVR (IF ran in VR, no Oculus/Meta support as of now.)
- Inference on GPU (Recommended):
- CUDA enabled GPU (NVIDIA ONLY), otherwise it will fall back to using CPU.
- ~5GB of storage space.
- ~1GB of available RAM.
- ~500MB of available VRAM.
- Inference on CPU:
- ~2GB of storage space.
- ~400MB of available RAM.
Depending on settings changed in the program those requirements can change rapidly.
v1.4.1 Changelog
- removes the requirements of git being installed by using a portable instance.
- If the portable instance doesnt exist, the locally installed version is used.
Known issues updating to this version from v1.3.x:
- Your custom bindings might have been reset and TextboxSTT might show up twice in the steamVR legacy binding UI.
To fix this, youll have to redo your bindings for the newly added version.
Full Changelog: v1.4.0...v1.4.1
Installing and Updating TextboxSTT
Install the Visual C++ Redistributables
After first launch, the TextboxSTT Launcher will tell you that the program is not yet installed and asks you if you want to only install the CPU dependencies:
After selecting an option (y = yes, n = no), No by default and recommended, TextboxSTT will start installing all the dependencies needed. This only has to be done once, after it will update dependencies whenever an update is available.
After the installation is done, TextboxSTT will start like normal.
To know whether an update is available, a button in the top right of the program will appear, informing you of a new update:
After clicking this button, the program will be updated and leads to a restart of the program. This process generally doesnt take much time.
v1.4.0 Updater Release
🢃 Download Release
Discord Support Server
With default settings, this program has following requirements:
- SteamVR (IF ran in VR, no Oculus/Meta support as of now.)
- Inference on GPU (Recommended):
- CUDA enabled GPU (NVIDIA ONLY), otherwise it will fall back to using CPU.
- ~5GB of storage space.
- ~1GB of available RAM.
- ~500MB of available VRAM.
- Inference on CPU:
- ~2GB of storage space.
- ~400MB of available RAM.
Depending on settings changed in the program those requirements can change rapidly.
v1.4.0 Changelog (This includes the Beta Changelog)
- Preloading the whisper model on startup, this should remove the increased latency on the first transcription.
- No redownloading of the program needed anymore! Download once, install once. You will get notified about new updates in TextboxSTT.
- TextboxSTT now comes with a portable python instance, that means required dependencies are now installed when needed.
- Added default word replacements for things like *, !, ?, .
- The "Reset Settings" button now resets all settings and restarts the program. (Word Replacements and Emotes are kept)
- The ⟳ button now restarts the program completely instead of reloading.
- The hotkey used by TextboxSTT now ignores input whenever you hold a modifier (CTRL, SHIFT etc.)
- You can now record a whole hotkey instead of just one key.
Known issues updating to this version from v1.3.x:
- Your custom bindings might have been reset and TextboxSTT might show up twice in the steamVR legacy binding UI.
To fix this, youll have to redo your bindings for the newly added version.
Full Changelog: v1.3.1...v1.4.0
Installing and Updating TextboxSTT
After first launch, the TextboxSTT Launcher will tell you that the program is not yet installed and asks you if you want to only install the CPU dependencies:
After selecting an option (y = yes, n = no), No by default and recommended, TextboxSTT will start installing all the dependencies needed. This only has to be done once, after it will update dependencies whenever an update is available.
After the installation is done, TextboxSTT will start like normal.
To know whether an update is available, a button in the top right of the program will appear, informing you of a new update:
After clicking this button, the program will be updated and leads to a restart of the program. This process generally doesnt take much time.
v1.4.0-Beta - Updater update!
🢃 Download Release
Discord Support Server
With default settings, this program has following requirements:
- SteamVR (IF ran in VR, no Oculus/Meta support as of now.)
- Inference on GPU (Recommended):
- CUDA enabled GPU (NVIDIA ONLY), otherwise it will fall back to using CPU.
- ~5GB of storage space.
- ~1GB of available RAM.
- ~500MB of available VRAM.
- Inference on CPU:
- ~2GB of storage space.
- ~400MB of available RAM.
Depending on settings changed in the program those requirements can change rapidly.
v1.4.0-Beta
- No redownloading of the program needed anymore!
- Download once, install once. You will get notified about new updates in TextboxSTT.
- TextboxSTT now comes with a portable python instance, that means required dependencies are now installed when needed.
- Added default word replacements for things like *, !, ?, .
- The "Reset Settings" button now resets all settings and restarts the program. (Word Replacements and Emotes are kept)
- The ⟳ button now restarts the program completely instead of reloading.
- The hotkey used by TextboxSTT now ignores input whenever you hold a modifier (CTRL, SHIFT etc.)
- You can now record a whole hotkey instead of just one key.
THIS IS A BETA RELEASE, please report any bugs to issues or the discord support server. This version will also update to Stable, when it is released.
DO NOT MODIFY THE CONTENTS OF THE "src" FOLDER! To take your config with you just place it in the same directory as "TextboxSTT.exe"
Known issues updating to this version:
- Your custom bindings might have been reset and TextboxSTT might show up twice in the steamVR legacy binding UI.
- To fix this, youll have to redo your bindings for the newly added version.
Full Changelog: v1.3.1...v1.4.0-Beta
Installing and Updating TextboxSTT
After first launch, the TextboxSTT Launcher will tell you that the program is not yet installed and asks you if you want to only install the CPU dependencies:
After selecting an option (y = yes, n = no), No by default and recommended, TextboxSTT will start installing all the dependencies needed. This only has to be done once, after it will update dependencies whenever an update is available.
After the installation is done, TextboxSTT will start like normal.
To know whether an update is available, a button in the top right of the program will appear, informing you of a new update:
After clicking this button, the program will be updated and leads to a restart of the program. This process generally doesnt take much time.
v1.3.1 rate limit hotfix
🢃 Download Release (Recommended)
🢃 Download CPU Only Version
Discord Support Server
With default settings, this program has following requirements:
- Inference on CPU:
- ~2GB of storage space.
- ~400MB of available RAM.
- Inference on GPU:
- CUDA enabled GPU (NVIDIA ONLY), otherwise it will fall back to using CPU.
- ~5GB of storage space.
- ~1GB of available RAM.
- ~500MB of available VRAM.
- SteamVR (IF ran in VR, no Oculus/Meta support as of now.)
Depending on settings changed in the program those requirements can change rapidly.
v1.3.1 Changelog
Fixes running into Rate limit issues when in mode "once". This fixes the issue of certain transcriptions not appearing in the Textbox.
Full Changelog: v1.3.0...v1.3.1
v1.3.0 OSC-Control, Autocorrection and VAD Update
🢃 Download Release
🢃 Download CPU Only Version
Discord Support Server
With default settings, this program has following requirements:
- Inference on CPU:
- ~2GB of storage space.
- ~400MB of available RAM.
- Inference on GPU:
- CUDA enabled GPU (NVIDIA ONLY), otherwise it will fall back to using CPU.
- ~5GB of storage space.
- ~1GB of available RAM.
- ~500MB of available VRAM.
- SteamVR (IF ran in VR, no Oculus/Meta support as of now.)
Depending on settings changed in the program those requirements can change rapidly.
v1.3.0 Changelog
- Control some TextboxSTT parameters over OSC in VRChat. Following parameters can be controlled:
- "use_kat" (boolean)
- "use_textbox" (boolean)
- "use_both" (boolean)
- "mode" (OSC parameter name "stt_mode") (integer)
- 0 -> once
- 1 -> once_continuous
- 2 -> realtime
- Add those parameters to your Expression Menu to control them.
- when adding a custom model for whisper, they are then saved in the settings, to remove one, select it and clear the textfield and press enter.
- Autocorrection for spelling in the Text to Text field. Supported languages are English, Polish, Turkish, Russian, Ukrainian, Czech, Portuguese, Greek, Italian, Vietnamese, French and Spanish.
- In mode "once_continuous" and "realtime", the program now tries to find sentence ends when transcriptions are taking too long, modifiable by the "max_transciption_time" setting for whisper.
- Silero Voice activity detection. Further adds voice activity detection to filter out pauses and static noise.
- obs only script, running "obs_only.exe" will run TextboxSTT in OBS only mode. with a simple console window and real time transcription.
Full Changelog: v1.2.0...v1.3.0
v1.2.0 - Translation Update
🢃 Download Release
🢃 Download CPU Only Version
Discord Support Server
With default settings, this program has following requirements:
- Inference on CPU:
- ~2GB of storage space.
- ~400MB of available RAM.
- Inference on GPU:
- CUDA enabled GPU (NVIDIA ONLY), otherwise it will fall back to using CPU.
- ~5GB of storage space.
- ~1GB of available RAM.
- ~500MB of available VRAM.
- SteamVR (IF ran in VR, no Oculus/Meta support as of now.)
Depending on settings changed in the program those requirements can change rapidly.
v1.2.0 Changelog
- Translation between languages, powered by M2M-100 using ctranslate2.
- Translate between any of the ~100 languages supported.
- Translation requires downloading the M2M-100 model into cache, which is another ~2GB.
- Inference is done on CPU by default, you can change this but i would advise against it, unless you have another 2GB of VRAM to spare.
- Text timeout is now handled by TextboxSTT, for more consistency between KAT, Textbox and the SteamVR Overlay.
- e.g. it will consistently populate the Textbox/KAT until either the Text timeout time is reached (30.0 seconds by default), or if it is cleared manually. Changing that value to <=0.0 will never clear the textbox, unless cleared manually.
- Changed the default "phrase_time_limit" from 2.0 to 1.0, for more "real time" transcriptions in modes "once_continuous" and "realtime"
v1.1.3 Changelog
- Fixed obs not launching unless reloading the program.
- added a typewriter effect to the OBS Source for better readability.
v1.1.2 Changelog
- Fixed context managing issue with audio source in mode once_continuous and realtime
- Try preventing SteamVR Overlay from freezing by switching Application type to Overlay and reinitializing OVR when error OverlayError_RequestFailed
v1.1.1 Changelog
- Automatically restarting the program when it is needed.
- Fixed obs browser source not launching.
- Fixed whisper transcribing random words when its only noise. (maybe use VAD in the future to avoid this issue and generally better results with transcription)
- Refactor and logging changes and fixes.
- Reverted some default value changes
v1.1.0 Changelog
- #2 allow use of user fine tuned models on Huggingface
- translation to english does not work with those models, at least with my testing.
- In the model section of the settings select "custom" and enter a path to a huggingface model: e.g. "openai/whisper-base": You can return to selection by pressing enter on an empty box.
TextboxSTT_n0NS2WHmrr.mp4
- complete config revamp, same (and more) config options but more organized!
- sadly for this version you cannot automatically take your old config with you, you can ask in the support discord on how to do that if you have alot of word replacements and/or emotes set.
- fast reload feature: click on the ⭯ button to quickly reload TextboxSTT
- added audio settings: added a gain slider and an individiual toggle for each audio feedback step.
- Shows transcribe times in main UI now.
- better log management, the program creates up to 5 logs, "latest.log" is the latest. logs are now saved in the "cache" folder.
- added a program icon, wowee
- Seperate windows are now always positioning relative to the window that it was opened from, not on the main window.
- lots of refactoring and additional error logging.
- updated to faster-whisper 0.3.0
- some smaller bugfixes
TextboxSTT v1.1.3
🢃 Download GPU Version
🢃 Download CPU Only Version
Discord Support Server
With default settings, this program has following requirements:
- CPU version:
- ~2GB of storage space.
- ~400MB of available RAM.
- GPU version:
- CUDA enabled GPU (NVIDIA ONLY), otherwise it will fall back to using CPU.
- ~5GB of storage space.
- ~1GB of available RAM.
- ~500MB of available VRAM.
- SteamVR (IF ran in VR, no Oculus/Meta support as of now.)
v1.1.3 Changelog
- Fixed obs not launching unless reloading the program.
- added a typewriter effect to the OBS Source for better readability.
v1.1.2 Changelog
- Fixed context managing issue with audio source in mode once_continuous and realtime
- Try preventing SteamVR Overlay from freezing by switching Application type to Overlay and reinitializing OVR when error OverlayError_RequestFailed
v1.1.1 Changelog
- Automatically restarting the program when it is needed.
- Fixed obs browser source not launching.
- Fixed whisper transcribing random words when its only noise. (maybe use VAD in the future to avoid this issue and generally better results with transcription)
- Refactor and logging changes and fixes.
- Reverted some default value changes
v1.1.0 Changelog
- #2 allow use of user fine tuned models on Huggingface
- translation to english does not work with those models, at least with my testing.
- In the model section of the settings select "custom" and enter a path to a huggingface model: e.g. "openai/whisper-base": You can return to selection by pressing enter on an empty box.
TextboxSTT_n0NS2WHmrr.mp4
- complete config revamp, same (and more) config options but more organized!
- sadly for this version you cannot automatically take your old config with you, you can ask in the support discord on how to do that if you have alot of word replacements and/or emotes set.
- fast reload feature: click on the ⭯ button to quickly reload TextboxSTT
- added audio settings: added a gain slider and an individiual toggle for each audio feedback step.
- Shows transcribe times in main UI now.
- better log management, the program creates up to 5 logs, "latest.log" is the latest. logs are now saved in the "cache" folder.
- added a program icon, wowee
- Seperate windows are now always positioning relative to the window that it was opened from, not on the main window.
- lots of refactoring and additional error logging.
- updated to faster-whisper 0.3.0
- some smaller bugfixes
TextboxSTT v1.1.2
🢃 Download GPU Version
🢃 Download CPU Only Version
Discord Support Server
With default settings, this program has following requirements:
- CPU version:
- ~2GB of storage space.
- ~400MB of available RAM.
- GPU version:
- CUDA enabled GPU (NVIDIA ONLY), otherwise it will fall back to using CPU.
- ~5GB of storage space.
- ~1GB of available RAM.
- ~500MB of available VRAM.
- SteamVR (IF ran in VR, no Oculus/Meta support as of now.)
v1.1.2 Changelog
- Fixed context managing issue with audio source in mode once_continuous and realtime
- Try preventing SteamVR Overlay from freezing by switching Application type to Overlay and reinitializing OVR when error OverlayError_RequestFailed
v1.1.1 Changelog
- Automatically restarting the program when it is needed.
- Fixed obs browser source not launching.
- Fixed whisper transcribing random words when its only noise. (maybe use VAD in the future to avoid this issue and generally better results with transcription)
- Refactor and logging changes and fixes.
- Reverted some default value changes
v1.1.0 Changelog
- #2 allow use of user fine tuned models on Huggingface
- translation to english does not work with those models, at least with my testing.
- In the model section of the settings select "custom" and enter a path to a huggingface model: e.g. "openai/whisper-base": You can return to selection by pressing enter on an empty box.
TextboxSTT_n0NS2WHmrr.mp4
- complete config revamp, same (and more) config options but more organized!
- sadly for this version you cannot automatically take your old config with you, you can ask in the support discord on how to do that if you have alot of word replacements and/or emotes set.
- fast reload feature: click on the ⭯ button to quickly reload TextboxSTT
- added audio settings: added a gain slider and an individiual toggle for each audio feedback step.
- Shows transcribe times in main UI now.
- better log management, the program creates up to 5 logs, "latest.log" is the latest. logs are now saved in the "cache" folder.
- added a program icon, wowee
- Seperate windows are now always positioning relative to the window that it was opened from, not on the main window.
- lots of refactoring and additional error logging.
- updated to faster-whisper 0.3.0
- some smaller bugfixes