Open crspeller opened 1 year ago
Wondering if this can be made available through an API to the plugin. I have the requirement of trimming audio and video files in a plugin and it would be great to share a common implementation. I'm currently using AWS Elastic Transcoder though a Go implementation would be more efficient as mentioned in the description
@mickmister @streamer45 It actually would be really great if this part could be done by the calls infrastructure. We already have that setup for generating transcriptions with calls.
Currently the audio summarization functionality will fail if the meeting is too long. (over 25MB) The first step to fixing this is being able to split up longer recordings and send them to the whisper API in chunks to avoid the API limitations: https://platform.openai.com/docs/guides/speech-to-text/introduction
Currently compression is used in this case: https://github.com/mattermost/mattermost-plugin-ai/blob/7a8c08f40e4051454ea68c872731e3b6e70c2123/server/meeting_summarization.go#L58
Go native implementation would be preferable to using ffmpeg.