.Ensure compatibility with numerous platforms, including.NET 6.0,. NET Platform 4.6.2, and.NET Specification 2.0 and above.Minimize addictions to prevent variation conflicts as well as the requirement for tiing redirects.Translating Sound Information.One of the primary capabilities of the SDK is actually audio transcription. Designers can easily translate audio data asynchronously or in real-time. Below is an instance of how to record an audio report:.utilizing AssemblyAI.utilizing AssemblyAI.Transcripts.var client = brand new AssemblyAIClient(" YOUR_API_KEY").var records = wait for client.Transcripts.TranscribeAsync( new TranscriptParams.AudioUrl="https://storage.googleapis.com/aai-docs-samples/nbc.mp3". ).transcript.EnsureStatusCompleted().Console.WriteLine( transcript.Text).For local area data, similar code may be used to obtain transcription.wait for utilizing var stream = new FileStream("./ nbc.mp3", FileMode.Open).var records = await client.Transcripts.TranscribeAsync(.flow,.brand-new TranscriptOptionalParams.LanguageCode = TranscriptLanguageCode.EnUs.).transcript.EnsureStatusCompleted().Console.WriteLine( transcript.Text).Real-Time Audio Transcription.The SDK additionally supports real-time audio transcription using Streaming Speech-to-Text. This attribute is particularly beneficial for requests calling for prompt handling of audio data.using AssemblyAI.Realtime.wait for making use of var scribe = brand new RealtimeTranscriber( new RealtimeTranscriberOptions.ApiKey="YOUR_API_KEY",.SampleRate = 16_000. ).transcriber.PartialTranscriptReceived.Subscribe( transcript =>Console.WriteLine($" Partial: transcript.Text "). ).transcriber.FinalTranscriptReceived.Subscribe( records =>Console.WriteLine($" Last: transcript.Text "). ).wait for transcriber.ConnectAsync().// Pseudocode for getting audio coming from a mic for instance.GetAudio( async (chunk) => wait for transcriber.SendAudioAsync( portion)).wait for transcriber.CloseAsync().Utilizing LeMUR for LLM Functions.The SDK integrates with LeMUR to allow designers to build big language style (LLM) applications on vocal information. Listed here is actually an instance:.var lemurTaskParams = new LemurTaskParams.Trigger="Offer a brief conclusion of the transcript.",.TranscriptIds = [transcript.Id],.FinalModel = LemurModel.AnthropicClaude3 _ 5_Sonnet..var reaction = wait for client.Lemur.TaskAsync( lemurTaskParams).Console.WriteLine( response.Response).Audio Cleverness Models.Furthermore, the SDK features integrated support for audio intelligence models, making it possible for belief review as well as various other innovative attributes.var records = wait for client.Transcripts.TranscribeAsync( brand-new TranscriptParams.AudioUrl="https://storage.googleapis.com/aai-docs-samples/nbc.mp3",.SentimentAnalysis = real. ).foreach (var result in transcript.SentimentAnalysisResults!).Console.WriteLine( result.Text).Console.WriteLine( result.Sentiment)// GOOD, NEUTRAL, or NEGATIVE.Console.WriteLine( result.Confidence).Console.WriteLine($" Timestamp: result.Start - result.End ").To read more, check out the official AssemblyAI blog.Image resource: Shutterstock.