I try to search over google alot, but not found the right solution for my case. I want to save my recognition to audio file with a specific config (https://cloud.google.com/speech-to-text/docs/reference/rest/v1/RecognitionConfig) and send it to Google Cloud, so they can translate my audio the right language i want.
Any chance i can do it? Thank you alot.
I try to search over google alot, but not found the right solution for my case. I want to save my recognition to audio file with a specific config (https://cloud.google.com/speech-to-text/docs/reference/rest/v1/RecognitionConfig) and send it to Google Cloud, so they can translate my audio the right language i want. Any chance i can do it? Thank you alot.