First month for free!

Get started

Lemonfox.ai

Lemonfox.ai

Docs
Easy-to-use AI API

Speaker Diarization API

Automatically identify who is speaking in your audio. Get speaker-labeled transcripts for meetings, podcasts, and interviews — at no extra cost.

Save 50% — Diarization Included

$0.17 / hour

Lemonfox.ai

with speaker labels

$0.36 / hour

OpenAI Whisper API

no diarization

Get StartedRead Docs

Identify Speakers

Automatically label up to 4 speakers in your audio. Each transcript segment includes a speaker tag like SPEAKER_00, so you know exactly who said what.

Built for Conversations

Perfect for meeting transcripts, podcast episodes, interview recordings, and call analytics. Combine with our LLM API to summarize multi-speaker conversations.

No Extra Charge

Speaker diarization is included in our base transcription price. Just $0.50 per 3 hours of audio — no per-speaker or diarization add-on fees.

Simple API Setup

Enable speaker diarization by setting speaker_labels to true and response_format to verbose_json. The response includes speaker labels on each segment and optional word-level timestamps.

const body = new FormData();
body.append('file', 'https://output.lemonfox.ai/wikipedia_ai.mp3');
body.append('response_format', 'verbose_json');
body.append('speaker_labels', 'true');

fetch('https://api.lemonfox.ai/v1/audio/transcriptions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY'
  },
  body: body
})
.then(response => response.json()).then(data => {
  data.segments.forEach(segment => {
    console.log(`[${segment.speaker}] ${segment.text}`);
  });
})
.catch(error => {
  console.error('Error:', error);
});
Read Docs

Frequently Asked Questions

Get Started

Other APIs: Speech-to-Text API, Whisper API, Subtitle API, DeepSeek API