Skip to main content

​
Learn how to enable sentence-level timestamps

Set word_timestamps=true in your Lightning STT query parameters. When diarization or timestamps are enabled, the response includes an utterances array that aggregates contiguous words into sentence-level segments.

​
Output format & field of interest

Each utterances entry contains text, start, end, and optional speaker fields. Use these sentence-level timestamps when you need to display readable captions, synchronize larger chunks of audio, or store structured call summaries.

​
Sample request

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

​
Sample response

{
  "transcription": "Hello world. How are you?",
  "utterances": [
    { "text": "Hello world.", "start": 0.0, "end": 0.9, "speaker": "speaker_0" },
    { "text": "How are you?", "start": 1.0, "end": 2.1, "speaker": "speaker_1" }
  ]
}