Word-level Timestamp

Enable use_word_timestamp to obtain per-word timing information in the response. Useful for precise subtitle sync or editing.

Name	Type	Default	Desc
use_word_timestamp	Boolean	false	When true, utterances include words with start_at, duration, and text.

Usage

In the POST Request body, set use_word_timestamp: true.

POST example: Example

Unified example (presets): Example

Example response

{
  "id": "G6j7wIYxSCCz3gYtQbeYdQ",
  "status": "completed",
  "results": {
    "utterances": [
      {
        "start_at": 1187,
        "duration": 600,
        "spk": 0,
        "spk_type": "NORMAL",
+       "words": [
+         {
+           "start_at": 1187,
+           "duration": 600,
+           "text": "Hello."
+         }
+       ],
        "msg": "Hello."
      }
      ]
    }
}

The response includes per-word timing under words.