Semantic Kernel is an SDK for multiple programming languages to develop applications with . However, LLMs only operate on textual data and don’t understand what is said in audio files. With the , you can use AssemblyAI’s transcription models using the to transcribe your audio and video files.
TranscriptPlugin
into your kernel:
Transcribe
function from the transcript plugin and invoke it with the context variables.
result.GetValue<string>()
.
You can also upload local audio and video file. To do this:
TranscriptPlugin.AllowFileSystemAccess
property to true
.INPUT
variable with a local file path.