> 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/frequently-asked-questions.md).
# Frequently Asked Questions
How does Transcribe store and process user data?
We strive to provide our users with full transparency about how we securely store and handle the data submitted by them. Generally, audio/video files supplied by the users are stored for up to 7 days, after which they are deleted permanently. These files and the transcriptions generated from them can also be deleted by the user at any time they choose, once the transcriptions are done. Please see the [Transcribe Data Privacy Policy](/ai-tools/data-privacy/transcribe-data-handling-level-3.md) page for more details.
Can anyone else have access to my data?
No. No one else is able to access your data.
Can I use my research data with Transcribe?
Transcribe is currently approved to handling data under Level 3 of Brown's [Data Risk Classification](https://it.brown.edu/policies/data-risk-classifications). Users who intend to use Transcribe with their research data should determine that their data falls under Data Risk Classification Level 3 and seek final approval from the IRB/HRPP office.
Does Transcribe use user data to train AI models?
No. Transcribe uses state-of-the-art Enterprise AI models and open source/open weight models to perform transcriptions. OIT/CCV does not train its own models or improve/fine-tune existing models.
Does Transcribe support translation?
Yes! As of Apr 10, 2026, The Gemini model now also supports translation. When [creating a job](/ai-tools/services/transcribe/creating-a-job.md), simply choose a target language that is different from the source language your audio/video media is in, and the transcription will be performed in that target language.
I am getting a "CUDA out of memory" error for my transcription jobs.
This can happen when the system is busy. Please try the same files again after 30 minutes or so.
I am getting a "Job Timed Out" error for my transcription jobs, or my transcription jobs are stuck in "in-progress" for a very long time.
This usually happens when the system is unable to process your files due to their format, especially if they are in .mp4 format. Please convert your files to WAVE (.wav) or MP3 (.mp3) formats and try again.
Are there any limits to using Transcribe?
Every user has a daily limit of 20 hours of audio/video media, and there is a per-job limit of 5 hours in duration and 1 GB in size.
Why can't download captions/subtitles from a job that has recently finished? The option is not available to me.
You might have submitted the job with the Gemini model. Captions/subtitles are not available for this model. Please feel free to resubmit a job with any other model.
---
# 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/frequently-asked-questions.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.