Skip to main content

​
Learn how to enable word timestamps

Add word_timestamps=true to your Lightning STT query parameters. This works for both raw-byte uploads (Content-Type: audio/wav) and JSON requests with hosted audio URLs.

​
Output format & field of interest

Responses include a word_timestamps array with word, start, end, and optional speaker labels (when diarization is enabled). Use these offsets to generate captions, subtitle tracks, or to align transcripts with downstream analytics.

​
Sample request

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

​
Sample response

{
  "status": "success",
  "transcription": "Hello world.",
  "word_timestamps": [
    { "word": "Hello", "start": 0.0, "end": 0.5, "speaker": "speaker_0" },
    { "word": "world.", "start": 0.6, "end": 0.9, "speaker": "speaker_0" }
  ],
  "utterances": [
    { "text": "Hello world.", "start": 0.0, "end": 0.9, "speaker": "speaker_0" }
  ]
}