Maze doesn’t build or train its own AI models. Instead, we partner with leading AI providers to power our intelligent features.
The AI features at Maze fall under two categories, each powered by specialized third-party providers:
1) Features powered by Large Language Models (LLMs) for intelligent data processing and conversation, including AI-moderated studies, Open Question Follow-ups, AI Themes, and Suggested Highlights.
These features utilize OpenAI and Anthropic LLMs. To access Anthropic models, we use Bedrock. To test, deploy, and monitor the performance of the features, we use Freeplay.
2) Features powered by Rev AI's automatic speech recognition (ASR) for voice-to-text transcriptions. This is used when transcribing Clips in unmoderated studies, and interviews in AI-moderated and 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: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Croatian, Czech, Danish, Dutch, English, Estonian, Farsi, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Mandarin Chinese (Simplified), Marathi, Nepali, Norwegian, Polish, Portuguese (Brazil), Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Welsh.