> 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.md).

# Transcribe

{% hint style="success" %}
**Data Privacy Notice:**\
The Transcribe Service is approved to handle sensitive data up to **Risk Level 3**. Before using Transcribe, please check [OIT's Data Risk Classifications](https://it.brown.edu/policies/data-risk-classifications) to understand what data can be used with Transcribe. Follow [data security best practices](/ai-tools/data-privacy/transcribe-data-handling-level-3/data-security-best-practices.md) when handling sensitive data.
{% endhint %}

## Main Features

**Live Site:** <https://ai.ccv.brown.edu/transcribe>

### Supported workflows

Transcribe can currently produce the following products:

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="image">Cover image</th></tr></thead><tbody><tr><td><h4>Transcriptions</h4></td><td>Accurately transcribe hours of interviews, focus groups, and other audio/video data for research in minutes.</td><td><a href="https://images.unsplash.com/photo-1544504729-982012fc43d0?crop=entropy&#x26;cs=srgb&#x26;fm=jpg&#x26;ixid=M3wxOTcwMjR8MHwxfHNlYXJjaHw0fHx0cmFuc2NyaXB0aW9ufGVufDB8fHx8MTc3OTM5NDgwMXww&#x26;ixlib=rb-4.1.0&#x26;q=85">https://images.unsplash.com/photo-1544504729-982012fc43d0?crop=entropy&#x26;cs=srgb&#x26;fm=jpg&#x26;ixid=M3wxOTcwMjR8MHwxfHNlYXJjaHw0fHx0cmFuc2NyaXB0aW9ufGVufDB8fHx8MTc3OTM5NDgwMXww&#x26;ixlib=rb-4.1.0&#x26;q=85</a></td></tr><tr><td><h4>Captions/Subtitles</h4></td><td>Generate time-synced captions/subtitles for audio and video media. Multiple formats supported.</td><td><a href="https://images.unsplash.com/photo-1641840296052-1b41c4bce493?crop=entropy&#x26;cs=srgb&#x26;fm=jpg&#x26;ixid=M3wxOTcwMjR8MHwxfHNlYXJjaHw0fHxjYXB0aW9uaW5nfGVufDB8fHx8MTc3OTM5NDUzNHww&#x26;ixlib=rb-4.1.0&#x26;q=85">https://images.unsplash.com/photo-1641840296052-1b41c4bce493?crop=entropy&#x26;cs=srgb&#x26;fm=jpg&#x26;ixid=M3wxOTcwMjR8MHwxfHNlYXJjaHw0fHxjYXB0aW9uaW5nfGVufDB8fHx8MTc3OTM5NDUzNHww&#x26;ixlib=rb-4.1.0&#x26;q=85</a></td></tr><tr><td><h4>Translation</h4></td><td>Transcribe speech in one language directly into text in another. No intermediate steps needed.</td><td><a href="https://images.unsplash.com/photo-1555564883-acd71fa27745?crop=entropy&#x26;cs=srgb&#x26;fm=jpg&#x26;ixid=M3wxOTcwMjR8MHwxfHNlYXJjaHwyfHx0cmFuc2xhdGV8ZW58MHx8fHwxNzc5Mzk0Mzk4fDA&#x26;ixlib=rb-4.1.0&#x26;q=85">https://images.unsplash.com/photo-1555564883-acd71fa27745?crop=entropy&#x26;cs=srgb&#x26;fm=jpg&#x26;ixid=M3wxOTcwMjR8MHwxfHNlYXJjaHwyfHx0cmFuc2xhdGV8ZW58MHx8fHwxNzc5Mzk0Mzk4fDA&#x26;ixlib=rb-4.1.0&#x26;q=85</a></td></tr></tbody></table>

### Feature highlights

* **Accuracy and speed** competitive with commercial offerings
* Supports **16 languages**
* Differentiates different speakers (**speaker diarization**)
* **Edit transcriptions**
* Supports transcription in **plain text** `.txt`) or Microsoft Word (`.docx`) formats
* Supports captions/subtitles in **SubRip** (`.srt`) and **WebVTT** (`.vtt`) formats
* **Translation** between 15 languages

{% hint style="danger" %}
**Any** machine-produced transcriptions, including those from *Transcribe*, must be reviewed and revised by a human to meet digital accessibility requirements. See [Getting Better Transcriptions](/ai-tools/services/transcribe/getting-better-transcriptions.md) and [Comparing Speech-to-text Models](/ai-tools/services/transcribe/comparing-speech-to-text-models.md) for best practices and model details.
{% endhint %}

## Data Privacy and Retention Policy

Brown must store your data on your behalf to do transcription services for you and play back your file while you review the work. For more information on how your data is processed and stored, please see [Transcribe Data Handling](/ai-tools/data-privacy/transcribe-data-handling-level-3.md).

{% hint style="warning" %}
*Transcribe* only stores audio and transcription data **temporarily**. It is not a long-term storage service. Download and securely store your transcriptions as soon as they are available. See [Downloading Transcriptions](/ai-tools/services/transcribe/downloading-transcriptions.md) for more information.\
OIT/CCV automatically deletes *Transcribe* audio after **7 days** and reserves the right to clear *Transcribe* of all data as needed. OIT/CCV is not responsible for any data loss resulting from use of this service. \
The [Brown University Code of Conduct](https://policy.brown.edu/policy/code-conduct) applies to *Transcribe* and all IT services at Brown.&#x20;
{% endhint %}

## Usage Limit

Each user has a daily usage limit of **20 hours** of total audio/video files. Once this limit is reached, the user will have to wait until the next day to submit more transcription jobs.


---

# 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:

```
GET https://docs.ccv.brown.edu/ai-tools/services/transcribe.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.