Support for longer video/audio files in Whisper model

[ioanmo226]

Describe the feature or improvement you're requesting

Currently, the Whisper model only supports video files that are up to 30 seconds long and audio files that are up to 25 MB in size.

This limitation can be a challenge for users who want to process longer video/audio files.

To overcome this limitation, I propose implementing a feature that allows the user to split their video/audio files into smaller segments and send multiple requests to the Whisper API to process each segment.

This will enable users to process longer video/audio files while still taking advantage of the Whisper model's powerful capabilities.

I would like to request the OpenAI team to consider implementing this feature or suggest any alternative solutions to handle longer videos/audio files using the Whisper model.

Additional context

No response