Retrieves the result of the transcription run using the provided run_id
.
run_id
that was assigned when you initially submitted your transcription request. This identifier allows our system to locate your specific transcription results within our processing infrastructure.
format_type
): Choose how your transcription is structured
txt
: Plain text format with speaker labels and timestamps (default)srt
: SubRip Text format, ready for subtitle integration in most video playersvtt
: WebVTT format, optimized for web-based video players and HTML5 applicationsdata_type
): Determine how youβll receive the transcription data
file
: Receive a pre-signed URL to download the complete transcription file (default)json
: Receive the raw transcription data directly in the API responsedata_type
parameter you specify in your request. Letβs explore both options in detail:
data_type=json
)Field | Description |
---|---|
start | The precise starting point of the speech segment (in seconds) |
end | The exact ending point of the speech segment (in seconds) |
text | The verbatim transcription of the spoken content in this segment |
speaker | Identifier for the person speaking during this segment |
data_type=file
)data_type=file
), the response provides a pre-signed URL that points to a file containing your transcription in the format you specified:
Field | Description |
---|---|
file_url | A temporary URL allowing you to download the transcription file |
expiry | Timestamp indicating when the download URL will expire |
format_type
selection:
format_type=txt
)format_type=srt
)format_type=vtt
)format_type=txt
) is ideal when you need:
format_type=srt
) is your best choice when:
format_type=vtt
) shines when:
The x-api-key
is a custom header required for authenticating requests to our API. Include this header in your request with the appropriate API key value to securely access our endpoints. You can find your API key(s) in the 'API' section of our studio website.
The unique identifier for the run, which was generated during the transcription creation process and returned upon task completion.
When set to true
, this parameter enables the generation of word-level timestamps in the response. These timestamps provide precise timing information for each word in the processed audio.
Successful Response
The response is of type DialogueItem Β· object[]
.