So i was trying to convert audio to text. I uploaded audio to Gemini 1.5 pro, but the text I’m getting as an output not of entire audio file but just some initial part.
Does anyone is facing same issue related to audio file?
Hi @Vaibhav
Welcome and Thanks for reaching out to the community!
I just wanted to let you know that I tested the audio extraction feature with a few different audio files, and it worked perfectly for me. It was able to extract the complete text from each file.
In case it’s helpful, I’ve attached some screenshots of the process for your reference.
Please let me know if you’re still having trouble or if you have any other questions.
Hi, thanks for reaching out to me. I have attached the screenshot of the error, I can’t convert the audio file (.wav) to text.
As Siva previously explained, this process works (in general). In your specific instance, the yellow-orange warning triangle indicates that some feature in the audio file triggered a content generation block.
This may sound odd, but I found it helps. Use the generate code button. Run the generated code in your development environment, not AI Studio. You will get the exact same block, but you then have better visibility into which code triggered. That might be helpful, or you might find it is triggering OTHER or perhaps RECITATION, in which case you probably can’t do much with Gemini and that specific audio file.