Plugins for Whispering Tiger
December 8, 2025 · View on GitHub
Current list of plugins that are available for Whispering Tiger.
If you have created a plugin, please add it to this list using a pull request or let me know and I will add it.
See plugin-creation.md for more information on how to create plugins yourself.
Installation of Plugins
Using Whispering Tiger UI Application (recommended):
Go to the Plugins Tab and click on the Download / Update Plugins Button.
Select the Plugin you want to install from the list and press Install.
(The Button might show ReInstall or Update depending on if the Plugin is already installed and is the current
version.)
Manual Installation:
Download the .py file and copy the plugin file into the Plugins directory in the root of the Whispering Tiger
folder.
List of Plugins
| Title | Preview | Description | Author |
|---|---|---|---|
| Keyboard Typing | <img src=Previews/Keyboard-Typing.gif width=250> | Type Text without your keyboard but instead with your Voice. supports additional customizable commands like: - start typing - stop typing - new line | Sharrnah |
| Subtitle Display | <img src=Previews/Subtitle-Display.gif width=250> | Display Subtitles everywhere on your Desktop | Sharrnah |
| Subtitles Export | <img src=Previews/Subtitles-Export.png width=250> | Generate Subtitle files for Audio or Video files. Can export as .VTT, .SRT or .SBV | Sharrnah |
| Audiobooks Generation | Generate long audiobooks from text - using high quality Text-to-Speech models. | Sharrnah | |
| OCR Monitor | <img src=Previews/OCR-Monitor.png width=250> | Select area that is monitored via Optical Character Recognition to translate or speak if the content changes | Sharrnah |
| Secondary Profile | <img src=Previews/Secondary-Profile.png width=250> | Load a secondary Profile at the same time, supporting a second recording and playback device selection. Does not load AI models a second time into memory. | Sharrnah |
| Voicevox Text 2 Speech | Japanese Text 2 Speech. change speaker of selected model in Text-to-Speech tab. acceleration_mode: can be "CPU" or "CUDA" thx to https://voicevox.hiroshiba.jp/ | Sharrnah | |
| TALQu3PRO Text 2 Speech | Japanese Text 2 Speech. Set the path to TALQuClient in General. thx to https://haruqa.github.io/TALQu/ | Rokujyushi | |
| Bark Text 2 Speech | Multilingual Text 2 Speech change history_prompt: to one of the voices you can find here: Bark Speaker Library prompt_wrap Setting can be used for more prompt features like: - singing (" ♪ ## ♪")- bias towards male or female (" [MAN] ##" or "[WOMAN] ##")- more infos in their Readme. thx to https://github.com/suno-ai/bark/ | Sharrnah | |
| Coqui Text 2 Speech | example generated with tts_models/en/vctk/vits | Multilingual Text 2 Speech Supports many different TTS Models, including: - Bark - Tortoise v2 - VITS - fairseq VITS (with ~1100 languages) - and many more. In addition it features a one-shot Voice Conversion model FreeVC which can be used with Text 2 Speech or Speech 2 Speech. (Plugin uses a locally running Coqui Server) thx to https://github.com/coqui-ai/TTS/ | Sharrnah |
| ElevenLabs Text 2 Speech | Multilingual Text 2 Speech (API). Set api_key: to your API key. change voice: to one of voices and voice_index: to the index of the voice. (other than 0 if more voices with same name exist) stt_*: Settings can limit the generation to prevent accidental use up of available chars on your account. thx to https://elevenlabs.io/ | Sharrnah | |
| ChatTTS Text 2 Speech | (currently) English and Chinese Only Text 2 Speech thx to https://github.com/2noise/ChatTTS | Sharrnah | |
| Mars5 Text 2 Speech | (currently) English Only Text 2 Speech thx to https://www.camb.ai/ | Sharrnah | |
| DeepL Text Translation | <img src=Previews/DeepL.png width=100> | DeepL Text Translation (API). Set auth_key: to your Authentication key. Be careful using it with realtime mode, as it might use up your characters fast. thx to https://www.deepl.com/ | Sharrnah |
| OpenAI API | <img src=Previews/OpenAI.png width=100> | OpenAI (API). Set api_key: to your API-Key. Provides Speech-to-Text, Text-to-Speech and Text-Translation using OpenAI Cloud Models Not recommended with Realtime mode because that can use up your Credits very quickly. thx to https://openai.com/ | Sharrnah |
| Gemini API | <img src=Previews/Gemini.png width=100> | Google Gemini (API). Set api_key: to your API-Key. Provides Speech-to-Text, Text-to-Speech and Text-Translation using Gemini Cloud Models Not recommended with Realtime mode because that can use up your Credits very quickly. thx to https://aistudio.google.com/ | Sharrnah |
| Deepgram API | <img src=Previews/Deepgram.png width=100> | Deepgram (API). Set api_key: to your API-Key. Provides Speech-to-Text and Text-to-Speech using Deepgram Cloud Models Not recommended with Realtime mode because that can use up your Credits very quickly. thx to https://deepgram.com/ | Sharrnah |
| Simple Soundboard | <img src=Previews/Soundboard.png width=250> | Provides a simple Soundboard where you can play audio files with a click of a button. Audio-files in sub-folders are grouped together. | Sharrnah |
| RVC Voice-Conversion Speech 2 Speech | Retrieval-based-Voice-Conversion Plugin. Use RVC models to convert: - Your speech (also in Realtime) - Any Text-to-Speech - Speech of audio-files into the models voice. | Sharrnah | |
| Large Language Model Conversation | <img src=Previews/LLM-Conversation.png width=250> | Implementation to run Large Language Models together with Whispering Tiger. | Sharrnah |
| Show currently playing song over OSC | <img src=Previews/Currently-Playing-Chatbox.gif width=250> | Displays the Song Title and Author of the Song you are currently listening to in your favourite music player inside VRChat using OSC. | Sharrnah |
| Volume and audio direction send over OSC | <img src=Previews/Audio-Direction-Avatar-Control.gif width=250> | Add the synced float parameters audio_volume and audio_direction to your VRChat avatar.
| Sharrnah |
| Control VRChat Avatar Parameters by Commands | <img src=Previews/Command-Avatar-Control.gif width=250> | Controls VRChat Avatar Parameters by custom commands. | Sharrnah |
| Control VRChat Avatar Parameters by Emotion Prediction | <img src=Previews/Text-Emotion-Avatar-Control.gif width=250> | Controls VRChat Avatar Parameters by Emotion Prediction. | Sharrnah |
| LLM Weather Function-Call Plugin | <img src=Previews/LLM-function-calling-weather.png width=250> | Allows asking a Large-Language-Model for the current weather of any City. (Currently supported by Phi-4 Multimodal LLM) | Sharrnah |