.Make certain compatibility with a number of platforms, including.NET 6.0,. Internet Framework 4.6.2, and.NET Specification 2.0 and also above.Decrease dependencies to avoid version problems and also the demand for binding redirects.Translating Audio Information.Among the primary capabilities of the SDK is actually audio transcription. Programmers may translate audio reports asynchronously or in real-time. Below is an instance of just how to translate an audio report:.using AssemblyAI.utilizing AssemblyAI.Transcripts.var client = brand-new AssemblyAIClient(" YOUR_API_KEY").var records = await client.Transcripts.TranscribeAsync( brand new TranscriptParams.AudioUrl="https://storage.googleapis.com/aai-docs-samples/nbc.mp3". ).transcript.EnsureStatusCompleted().Console.WriteLine( transcript.Text).For local data, similar code may be used to attain transcription.wait for using var stream = brand new FileStream("./ nbc.mp3", FileMode.Open).var records = await client.Transcripts.TranscribeAsync(.stream,.brand-new TranscriptOptionalParams.LanguageCode = TranscriptLanguageCode.EnUs.).transcript.EnsureStatusCompleted().Console.WriteLine( transcript.Text).Real-Time Audio Transcription.The SDK additionally sustains real-time sound transcription using Streaming Speech-to-Text. This attribute is particularly valuable for uses demanding urgent processing of audio data.using AssemblyAI.Realtime.wait for making use of var scribe = brand-new RealtimeTranscriber( brand-new RealtimeTranscriberOptions.ApiKey="YOUR_API_KEY",.SampleRate = 16_000. ).transcriber.PartialTranscriptReceived.Subscribe( transcript =>Console.WriteLine($" Limited: transcript.Text "). ).transcriber.FinalTranscriptReceived.Subscribe( records =>Console.WriteLine($" Ultimate: transcript.Text "). ).await transcriber.ConnectAsync().// Pseudocode for obtaining sound from a microphone for instance.GetAudio( async (part) => await transcriber.SendAudioAsync( portion)).wait for transcriber.CloseAsync().Using LeMUR for LLM Apps.The SDK integrates along with LeMUR to make it possible for developers to create sizable language design (LLM) apps on vocal data. Listed below is actually an instance:.var lemurTaskParams = brand-new LemurTaskParams.Cause="Deliver a quick review of the transcript.",.TranscriptIds = [transcript.Id],.FinalModel = LemurModel.AnthropicClaude3 _ 5_Sonnet..var feedback = wait for client.Lemur.TaskAsync( lemurTaskParams).Console.WriteLine( response.Response).Audio Cleverness Versions.Also, the SDK includes built-in support for audio knowledge models, allowing sentiment analysis and also various other enhanced attributes.var transcript = await client.Transcripts.TranscribeAsync( new TranscriptParams.AudioUrl="https://storage.googleapis.com/aai-docs-samples/nbc.mp3",.SentimentAnalysis = real. ).foreach (var cause transcript.SentimentAnalysisResults!).Console.WriteLine( result.Text).Console.WriteLine( result.Sentiment)// POSITIVE, NEUTRAL, or downside.Console.WriteLine( result.Confidence).Console.WriteLine($" Timestamp: result.Start - result.End ").To read more, see the official AssemblyAI blog.Image resource: Shutterstock.