Runtime Speech Recognizer (Real-Time, Offline, AI)

Publish date

2025-11-13

Asset Description

Transform your game with real-time, offline, cross-platform speech recognition powered by OpenAI Whisper technology!

General Information

ℹ️ Note: The images with plugin examples and the demo project were created using the Runtime Audio Importer plugin. So, to follow these examples, you will need to install that plugin as well. However, you can also implement your own audio input solution without using it.

Experience fast cross-platform speech / voice recognition that works completely offline, featuring GPU acceleration on Windows and optimized CPU processing on other platforms. Integrate voice-driven menus, hands-free gameplay commands, or specialized assistive features with ease.

Key features:

Real-time Recognition: Convert speech to text instantly as your players speak
Offline Operation: No internet connection required - everything runs locally
High Performance:
- Windows: Vulkan-powered GPU acceleration
- Mac and iOS: Metal-powered GPU acceleration
- Other Platforms: Optimized CPU processing with intrinsics (may be slower, such as on Android or Meta Quest, when running natively)
Cross-Platform: Works seamlessly across all platforms
Multi-Language Support: Recognize and translate 95+ languages with automatic language detection
Flexible Integration: Works with any audio input source
Voice Activity and Command Detection: Smart noise filtering and command detection for accurate results
Customizable Parameters: Fine-tune the recognition process for your needs

Supported languages:

Auto (The language is detected automatically)
🇺🇸 English (En)
🇨🇳 Chinese (Zh)
🇩🇪 German (De)
🇪🇸 Spanish (Es)
🇷🇺 Russian (Ru)
🇰🇷 Korean (Ko)
🇫🇷 French (Fr)
🇯🇵 Japanese (Ja)
🇵🇹 Portuguese (Pt)
🇹🇷 Turkish (Tr)
🇵🇱 Polish (Pl)
🇦🇩 Catalan (Ca)
🇳🇱 Dutch (Nl)
🇦🇪 Arabic (Ar)
🇸🇪 Swedish (Sv)
🇮🇹 Italian (It)
🇮🇩 Indonesian (Id)
🇮🇳 Hindi (Hi)
🇫🇮 Finnish (Fi)
🇻🇳 Vietnamese (Vi)
🇮🇱 Hebrew (Iw)
🇺🇦 Ukrainian (Uk)
🇬🇷 Greek (El)
🇲🇾 Malay (Ms)
🇨🇿 Czech (Cs)
🇷🇴 Romanian (Ro)
🇩🇰 Danish (Da)
🇭🇺 Hungarian (Hu)
🇮🇳 Tamil (Ta)
🇳🇴 Norwegian (No)
🇹🇭 Thai (Th)
🇵🇰 Urdu (Ur)
🇭🇷 Croatian (Hr)
🇧🇬 Bulgarian (Bg)
🇱🇹 Lithuanian (Lt)
🇻🇦 Latin (La)
🇳🇿 Maori (Mi)
🇮🇳 Malayalam (Ml)
🏴 Welsh (Cy)
🇸🇰 Slovak (Sk)
🇮🇳 Telugu (Te)
🇮🇷 Persian (Fa)
🇱🇻 Latvian (Lv)
🇧🇩 Bengali (Bn)
🇷🇸 Serbian (Sr)
🇦🇿 Azerbaijani (Az)
🇸🇮 Slovenian (Sl)
🇮🇳 Kannada (Kn)
🇪🇪 Estonian (Et)
🇲🇰 Macedonian (Mk)
🇫🇷 Breton (Br)
🇪🇸 Basque (Eu)
🇮🇸 Icelandic (Is)
🇦🇲 Armenian (Hy)
🇳🇵 Nepali (Ne)
🇲🇳 Mongolian (Mn)
🇧🇦 Bosnian (Bs)
🇰🇿 Kazakh (Kk)
🇦🇱 Albanian (Sq)
🇰🇪 Swahili (Sw)
🇪🇸 Galician (Gl)
🇮🇳 Marathi (Mr)
🇮🇳 Punjabi (Pa)
🇱🇰 Sinhala (Si)
🇰🇭 Khmer (Km)
🇿🇼 Shona (Sn)
🇳🇬 Yoruba (Yo)
🇸🇴 Somali (So)
🇿🇦 Afrikaans (Af)
🇫🇷 Occitan (Oc)
🇬🇪 Georgian (Ka)
🇧🇾 Belarusian (Be)
🇹🇯 Tajik (Tg)
🇵🇰 Sindhi (Sd)
🇮🇳 Gujarati (Gu)
🇪🇹 Amharic (Am)
🇮🇱 Yiddish (Yi)
🇱🇦 Lao (Lo)
🇺🇿 Uzbek (Uz)
🇫🇴 Faroese (Fo)
🇭🇹 Haitian Creole (Ht)
🇦🇫 Pashto (Ps)
🇹🇲 Turkmen (Tk)
🇳🇴 Nynorsk (Nn)
🇲🇹 Maltese (Mt)
🇮🇳 Sanskrit (Sa)
🇱🇺 Luxembourgish (Lb)
🇲🇲 Myanmar (My)
🇹🇱 Tibetan (Bo)
🇵🇭 Tagalog (Tl)
🇲🇬 Malagasy (Mg)
🇮🇳 Assamese (As)
🇷🇺 Tatar (Tt)
🇺🇸 Hawaiian (Haw)
🇨🇩 Lingala (Ln)
🇳🇬 Hausa (Ha)
🇷🇺 Bashkir (Ba)
🇮🇩 Javanese (Jw)
🇮🇩 Sundanese (Su)
🇭🇰 Cantonese (Yue)

Technical details

Features:

Fast recognition speed (with Vulkan GPU acceleration on Windows and Metal GPU acceleration on Mac/iOS), real-time to near-real-time
English-only and multilingual models available, with multilingual supporting 100 languages
Automatic language detection for multilingual recognition
Different model sizes available (from 75 Mb to 2.9 Gb)
Automatic download of language models in the Editor
Optional translation of recognized speech to English
Customizable properties
Easy selection of model size and language in settings
No static libraries or external dependencies
Cross-platform compatibility (Windows, Mac, Linux, Android, iOS, etc)