Hi, I am intending to use the gemini 2.0 api as a real time Speech to text agent. I have been using Google speech to text as well but it has its limitations such as you cannot list more than certain languages in the configuration. I am looking for a solution where a user could speak in atleast 4 languages and upon initial testing gemini 2.0 with the right prompts seems to work.
I wanted to know does gemini 2.0 support this officially as the documentation does say that gemini models are trained on a bunch of languages or is it officially only supported for english but still works for other languages ?
Thank you for your time and looking forward to your response.