Timestamp From Audio

Creates a new transcription that extracts text and time information from the audio generated by a text-to-speech (TTS) generation.

For example, you can generate SRT subtitles with the timestamps at word or sentence level.

Similarly, you can also generate VRT or JSON outputs, similarly, with the timestamps at word or sentence level.

The audio to be transcribed comes from a text-to-speech (TTS) generation. The TTS job ID is specified in the request body.

The API responds with information about the newly created Transcription job:

  • Status: 201 - Created
  • Header: Location: /api/v2/transcriptions/{id} - the URL for the recently-created job
  • Body: Job data (job ID and status)

When the job completes, the transcription result is delivered through the webhook sent to the webhook_url specified in the request body.

Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…
Body Params
string
required

The TTS job ID of the audio to be transcribed.

string

The URL of the webhook that is called when the transcription job completes.

string
enum
required

The format of the transcription result.

Allowed:
string
enum
required

Determines the level of timestamps in the transcription result. The timestamps can be created for each word or for each sentence.

Allowed:
Responses

Language
Credentials
LoadingLoading…
Response
Click Try It! to start a request and see the response here! Or choose an example:
application/json