multimodal audio in vs. transcribing an audio attachment?

[ghchinoy]

Currently, it appears that audio is handled as a binary attachment, and is then transcribed. ref

ai/lib/src/views/llm_chat_view/llm_chat_view.dart

Line 230 in b1fbc7c

Future<void> _onTranslateStt(XFile file) async {

For multimodal models such as Gemini, audio as an input is natively supported.

The expectation is that instead of an audio attachment that is transcribed, the audio should be used as the input to the model directly rather than the transcription.