> For the complete documentation index, see [llms.txt](https://docs.ccv.brown.edu/ai-tools/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ccv.brown.edu/ai-tools/services/transcribe/downloading-transcriptions.md).
# Downloading Transcriptions
{% hint style="info" %}
Starting in Transcribe 1.1.3 you can download word-level timestamps as a json file and enhanced caption files in SRT (`.srt`) and WebVTT (`.vtt`) formats from transcriptions done with the Whisper, Qwen, and Cohere models. See [Captions/Subtitles](/ai-tools/services/transcribe/downloading-transcriptions/subtitles.md).
Starting in Transcribe 1.0.6, you can download transcriptions in bulk from the View Job page.
{% endhint %}
## 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 or .vtt) (Not supported by the Gemini model)
* Word-level timestamps (.json) (Not supported by the Gemini model)
{% hint style="warning" %}
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.
{% endhint %}
## 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 or .vtt) (Not supported by the Gemini model)
* Word-level timestamps (.json) (Not supported by the Gemini model)
{% hint style="info" %}
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.
{% endhint %}
{% hint style="warning" %}
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.
{% endhint %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.ccv.brown.edu/ai-tools/services/transcribe/downloading-transcriptions.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.