Speaker Diarization

Unlock the full power of your audio content with industry-leading speaker diarization. Identify speakers to create structured, speaker-labeled transcripts that bring clarity to even the most complex conversations.

Use our API

Get started with less than 10 lines of code

Simply enable Speaker Diarization in our API, and receive a detailed transcript with a list of utterances.

See how in docs

1import assemblyai as aai
2
3aai.settings.api_key = "YOUR_API_KEY"
4
5transcriber = aai.Transcriber()
6
7audio_url = (
8    "https://assembly.ai/sports_injuries.mp3"
9)
10
11config = aai.TranscriptionConfig(speaker_labels=True)
12
13transcript = transcriber.transcribe(audio_url, config)
14
15print(transcript.text)
16
17for utterance in transcript.utterances:
18    print(f"Speaker {utterance.speaker}: {utterance.text}")

1import { AssemblyAI } from 'assemblyai'
2
3const client = new AssemblyAI({
4  apiKey: 'YOUR_API_KEY'
5})
6
7const audioUrl =
8  'https://assembly.ai/sports_injuries.mp3'
9
10const params = {
11  audio: audioUrl,
12  speaker_labels: true
13}
14
15const run = async () => {
16  const transcript = await client.transcripts.transcribe(params)
17  console.log(transcript.text)
18
19  for (let utterance of transcript.utterances!) {
20    console.log(`Speaker ${utterance.speaker}: ${utterance.text}`)
21  }
22}
23
24run()

1package main
2
3import (
4    "context"
5    "fmt"
6    "os"
7
8    aai "github.com/AssemblyAI/assemblyai-go-sdk"
9)
10
11func main() {
12    ctx := context.Background()
13
14    audioURL := "https://assembly.ai/sports_injuries.mp3"
15
16    client := aai.NewClient("YOUR_API_KEY")
17
18    params := &aai.TranscriptOptionalParams{
19        SpeakerLabels: aai.Bool(true),
20    }
21
22    transcript, err := client.Transcripts.TranscribeFromURL(ctx, audioURL, params)
23    if err != nil {
24        fmt.Println("Something bad happened:", err)
25        os.Exit(1)
26    }
27
28    fmt.Println(*transcript.Text)
29
30    for _, utterance := range transcript.Utterances {
31        fmt.Printf("Speaker %v: %v
32", *utterance.Speaker, *utterance.Text)
33    }
34}

1import com.assemblyai.api.AssemblyAI;
2import com.assemblyai.api.resources.transcripts.types.*;
3
4public final class App {
5    public static void main(String[] args) {
6        AssemblyAI client = AssemblyAI.builder()
7                .apiKey("YOUR_API_KEY")
8                .build();
9
10        String audioUrl = "https://assembly.ai/sports_injuries.mp3";
11
12        var params = TranscriptOptionalParams.builder()
13                .speakerLabels(true)
14                .build();
15
16        Transcript transcript = client.transcripts().transcribe(audioUrl, params);
17
18        System.out.println(transcript.getText().get());
19
20        transcript.getUtterances().get().forEach(utterance ->
21            System.out.println("Speaker " + utterance.getSpeaker() + ": " + utterance.getText())
22        );
23    }
24}

1require 'assemblyai'
2
3client = AssemblyAI::Client.new(api_key: 'YOUR_API_KEY')
4
5audio_url = 'https://assembly.ai/sports_injuries.mp3'
6
7transcript = client.transcripts.transcribe(
8  audio_url: audio_url,
9  speaker_labels: true
10)
11
12abort transcript.error if transcript.status == AssemblyAI::Transcripts::TranscriptStatus::ERROR
13
14puts transcript.text
15
16transcript.utterances.each do |utterance|
17  printf('Speaker %<speaker>s: %<text>s', speaker: utterance.speaker, text: utterance.text)
18end

Improve transcription quality and readability

Reduce speaker misattribution and transcription errors, enabling cleaner data for NLP tasks and enhancing user experience in speech-to-text applications.

See benchmarks and latest improvements

Build confidently with accurate, multilingual speaker diarization

Maximize speaker count accuracy

Enhance conversation analysis and speaker-dependent AI models with industry-leading speaker count accuracy. Our models achieve a 2.9% error rate, outperforming competitors in identifying the number of speakers.

See benchmarks and latest improvements

Broaden your application's reach

Support speaker diarization in 95 languages, enabling multilingual audio analysis and expanding your product's global market potential.

See how in docs

Make every voice count

Improve the readability of your transcriptions	Unlock call center insights	Create a better search experience	Assess communication patterns
Optimize short-form content generation	Enhance automated dubbing precision	Implement intelligent camera focus	Determine talk time for sales teams

Join 200K+ developers building new experiences with voice data

CEO at Vidyo

"We have had a phenomenal experience so far. The integration was simple and easy for developers to get started. The accuracy is better than any other tools in the market (and we have tried them all). Highly recommend!"

CEO at Pathlight

"Works incredibly well out of the box. Allowed us to focus on product instead of infrastructure. As a result, we were able to bring a transformative new product to market in half the time."

Product Manager at Aloware

"The accuracy was strong, but the great documentation and unique models like Auto Chapters and Sentiment Analysis is what really won us over."

Chief Product Officer at CallRail

"Partnering with AssemblyAI has made it easy for us to deliver world-class voice intelligence powered by market-leading speech-to-text technology."

Turn voice data into unparalleled product experiences

Partner with the leader in Speech AI to build powerful products with breakthrough industry impact.

Try our API for free Contact sales