Skip to main content

​
Learn how to enable speaker diarization

Pass diarize=true when calling the Lightning STT POST endpoint. The parameter can be combined with other enrichment options (timestamps, emotions, etc.) without changing your audio payload.

​
Output format & field of interest

When enabled, every entry in word_timestamps includes a speaker field (speaker_0, speaker_1, …). The utterances array also carries speaker labels so you can reconstruct conversations, build turn-taking analytics, or display multi-speaker captions.

​
Sample request

curl --request POST \
  --url "https://waves-api.smallest.ai/api/v1/lightning/get_text?model=lightning&language=en&diarize=true&word_timestamps=true" \
  --header "Authorization: Bearer $SMALLEST_API_KEY" \
  --header "Content-Type: audio/wav" \
  --data-binary "@/path/to/two-speaker.wav"

​
Sample response

{
  "transcription": "Agent: Hello world. Customer: Hi there.",
  "word_timestamps": [
    { "word": "Hello", "start": 0.0, "end": 0.4, "speaker": "speaker_0" },
    { "word": "world.", "start": 0.4, "end": 0.8, "speaker": "speaker_0" },
    { "word": "Hi", "start": 1.0, "end": 1.2, "speaker": "speaker_1" },
    { "word": "there.", "start": 1.2, "end": 1.6, "speaker": "speaker_1" }
  ],
  "utterances": [
    { "text": "Hello world.", "start": 0.0, "end": 0.8, "speaker": "speaker_0" },
    { "text": "Hi there.", "start": 1.0, "end": 1.6, "speaker": "speaker_1" }
  ]
}