Downloading Transcriptions

This page discusses how you can download your transcripts in different formats.

Starting in Transcribe 1.0.7, you can download word-level timestamps as a json file and enhanced SRT captions from transcriptions done with the Whisper and Qwen model. See Captions/Subtitles.

Starting in Transcribe 1.0.6, you can download transcriptions in bulk from the View Job page.

Downloading a single transcript

On the View Transcription page, you can click the hamburger menu button on the top right of the page to open a drop down menu (shown below). From this menu, you can either copy the transcript to the clipboard or download the transcript. We support the following formats when you are downloading a transcript:

• Text file (.txt)

• Word document (.docx)

• Captions (.srt) (Whisper and Qwen only)

• Word-level timestamps (.json) (Whisper and Qwen only)

Both enhanced captions and word-level timestamps options will use the raw word-level timestamps produced by the ASR model to output the files for download, which means that manual edits to the transcription segments in the View Transcription page will not be applied to these files. For users using word-level timestamps, we recommend that you directly edit the files that you download.

Downloading all transcripts in a job

On the View Job page, you can open the hamburger menu on the top right of the page to open a dropdown menu shown below, where you can choose to download all transcripts in a job.

Once you click Download all transcripts, a dialog (shown below) will be open, where you can choose the format of the transcripts. You can also choose whether to group all consecutive sentences by the same speaker in the downloaded transcript. Click Download to start downloading.

We support the following formats when you are downloading a transcript:

• Text file (.txt)

• Word document (.docx)

• Captions (.srt) (Whisper only)

• Word-level timestamps (.json) (Whisper only)

If there is only one file in a job, the format of the downloaded file will be the one that you choose. If more than one file exists in your job, then the downloaded file will be packages in a zip file, in which all files in the archive will be in the format that you choose.

Both enhanced captions and word-level timestamps options will use the raw word-level timestamps produced by the ASR model to output the files for download, which means that manual edits to the transcription segments in the View Transcription page will not be applied to these files. For users using word-level timestamps, we recommend that you directly edit the files that you download.