Maze doesn’t build or train its own AI models.
The Maze AI features fall under two separate categories, powered by the respective providers:
-
Features that use OpenAI’s GPT large language model (LLM) for intelligent data processing
This includes features such as Open Questions with follow-ups, Themes, and AI suggestions. -
Features powered by Rev AI's automatic speech recognition (ASR) for voice-to-text transcriptions
This includes Interview Studies.
OpenAI multilingual support
GPT-4 supports English as its primary language. It also handles other languages well, as it was trained on a variety of multilingual internet text, although its capabilities in each language may vary.
Generally, it performs best in languages with more extensive training data. For less widely spoken languages or those with less available training data, performance might not be as strong or nuanced. We recommend previewing and testing to confirm that the block performs well in your desired language.
It supports text generation and understanding in various languages, including but not limited to: Arabic, Chinese (Simplified and Traditional), Czech, Danish, Dutch, English, Finnish, French, German, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese (Brazilian and European), Romanian, Russian, Spanish, Swedish, Thai, Turkish, Ukrainian, and Vietnamese.
The exact number of supported languages can change as OpenAI continues to update and improve GPT-4. Future updates may enhance its capabilities in existing languages or add support for new ones.
Learn more in OpenAI’s official documentation
Rev AI multilingual support
Rev AI has been trained on a range of global voices to make sure that the engine can accurately recognize and transcribe speech from different languages and accents.
It supports the following languages: Arabic, Czech, Danish, Dutch, English, Finnish, French, German, Greek, Hungarian, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Romanian, Russian, Spanish, Swedish, and Turkish.