Introducing the AssemblyAI Java SDK

We are thrilled to release the AssemblyAI Java SDK. You can use the SDK to transcribe audio asynchronously or in real-time, use our audio intelligence model, and apply LLMs to your audio data using LeMUR.

Here are a couple of examples showcasing the Java SDK.

1. Transcribe an audio file

import com.assemblyai.api.AssemblyAI;
import com.assemblyai.api.resources.transcripts.types.Transcript;

AssemblyAI client = AssemblyAI.builder()
    .apiKey(System.getenv("ASSEMBLYAI_API_KEY"))
    .build();

Transcript transcript = client.transcripts().transcribe(
    "https://storage.googleapis.com/aai-docs-samples/nbc.mp3",
);
System.out.println(transcript);

You can also transcribe a local file, as shown here.

Transcript transcript = client.transcripts().transcribe(new File("./news.mp4"));
System.out.println(transcript);

Learn how to transcribe audio files by following the step-by-step instructions in our docs.

2. Transcribe audio in real-time

import com.assemblyai.api.RealtimeTranscriber;

RealtimeTranscriber realtimeTranscriber = RealtimeTranscriber.builder()
    .apiKey(System.getenv("ASSEMBLYAI_API_KEY"))
    .onSessionStart(System.out::println)
    .onPartialTranscript(System.out::println)
    .onFinalTranscript(System.out::println)
    .onError((err) -> System.out.println(err.getMessage()))
    .build();

realtimeTranscriber.connect();

// Pseudo code for getting audio from a microphone for example
getAudio((chunk) -> realtimeTranscriber.sendAudio(chunk));

realtimeTranscriber.close();

Learn how to transcribe audio from the microphone by following the step-by-step instructions in our docs.

3. Use LeMUR to build LLM apps on voice data

import com.assemblyai.api.AssemblyAI;
import com.assemblyai.api.resources.transcripts.types.Transcript;
import com.assemblyai.api.resources.lemur.requests.LemurTaskParams;
import com.assemblyai.api.resources.lemur.types.LemurTaskResponse;

LemurTaskResponse response = client.lemur().task(LemurTaskParams.builder()
        .prompt("Summarize this transcript.")
        .transcriptIds(List.of(transcript.getId()))
        .build());

System.out.println(response.getResponse());

Learn how to use LLMs with audio data using LeMUR in our docs.

4. Use audio intelligence models

import com.assemblyai.api.AssemblyAI;
import com.assemblyai.api.RealtimeTranscriber;
import com.assemblyai.api.resources.transcripts.types.*;

Transcript transcript = aai.transcripts().transcribe(
        "https://storage.googleapis.com/aai-docs-samples/nbc.mp3",
        TranscriptOptionalParams.builder()
                .sentimentAnalysis(true)
                .build()
);
for(SentimentAnalysisResult result: transcript.getSentimentAnalysisResults().get())
{
    System.out.println("Text: " + result.getText());
    System.out.println("Sentiment: " + result.getSentiment());
    System.out.println("Confidence: " + result.getConfidence());
    System.out.printf("Timestamp: %s - %s", result.getStart(), result.getEnd());
}

Learn more about our audio intelligence models in our docs.