Hi Everyone! I’m using Whisper to transcribe some audio files. My files are in .wav format. Whisper has a 25 MB limit. I would like know if there is a way (tool/plugin) I can break my files into multiple ones in Bubble. I would greatly appreciate your help! Thank you!
Switch to Google Cloud
You probably want to convert to mp3 rather than split into chunks. Many APIs will do this for you (e.g WAV to MP3 | CloudConvert) or you can create one yourself if you know how
is this what you want (minus the video, or video too)?
Haha that’s a great suggestion and alternative. I have tried a few other tools (AssemblyAI and Deepgram) and I noticed that you can’t really have them run in the background of a Zoom call. Is that the case for the Google one?
Ahh I will give this a shot. Thank you!
Just ran a couple of tests on this. It seems like the conversion from .wav to mp3 reduces the size by 10x. For instance a 33MB .wav file ( ~3 min audio recording) would be a 3.3 MB mp3 file, which allows me to upload larger files when in mp3, but would still encounter the issue at some point (for instance when recording is 30min+) which is why I thought breaking them into chunks might do the the job. Thank you so much for your input though! It’s helpful.
Please ignore my comment above lol. It’s more of an issue with the audio recorder. Thank you!
hey! would you recommend Google Cloud over Whisper? We’re trying to figure out what the best option is for files over 75MB.
I have not used either one, but I would look at the API docs for Google and see if they mention any file size limits
The stated limit for Google Cloud Speech-to-Text is 480min in asynchronous mode. Confident your 75 MB .wav file isn’t an issue.