This work was developed in CTL Seminar A Deep Dive into Advising and AI in Spring 2024. In this example set, one short introduction document about LaGuardia Community College has been translated into the top 23 languages spoken at LaGuardia. The following AI tools were used to generate examples:
It took about 1.5 hours to process all requests and cost $2.84.
Below is the screenshot of the list of top 24 languages spoken at LaGuardia Community College. The complete slide deck is available at here .
For corrections and feedback, contact Tomonori Nagano at tnagano@lagcc.cuny.edu .
"Using this text and other available resources/information, explain to [LANGUAGE] speakers who are not familiar with the American higher education why they should go to a community college. Use [LANGUAGE]."
"Using this text and other available resources/information, explain to [LANGUAGE] speakers who are not familiar with the American higher education why they should go to a community college. Use [LANGUAGE]."
"Using this text and other available resources/information, explain to [LANGUAGE] speakers who are not familiar with the American higher education why they should go to a community college. Use [LANGUAGE]."
"Using this text and other available resources/information, explain to [LANGUAGE] speakers who are not familiar with the American higher education why they should go to a community college. Use [LANGUAGE]."
This work was developed in CTL Generative AI Institute at LaGuardia Community College in 2024-2025.
OpenAI has developed Whisper (https://github.com/openai/whisper), a general-purpose speech recognition model that can transcribe speech files into text and generate speech from text. This is a specific-purpose large language model (often used synonymously with AI), and the model has been trained on nearly 100 different languages. According to OpenAI's website (https://platform.openai.com/docs/guides/speech-to-text/supported-languages/), Whisper officially supports the following languages: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Welsh.
In March 2025, ChatGPT announced a newer model for TTS (speech transcription) called "gpt-4o-mini-tts." This new model can not only generate audio from text with higher accuracy, but it can also instruct how the speech should sound (e.g., calm, professional, bedtime story, etc.). In this project, I have tried the "gpt-4o-mini-tts" model with multilingual texts (the original and translated versions of "The Hare and the Tortoise").
Last update: