> For the complete documentation index, see [llms.txt](https://guide.scribe.gov.sg/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guide.scribe.gov.sg/help/faqs/transcripts.md).

# Transcripts

{% hint style="danger" %}
**Scribe uses advanced audio/language processing techniques and will have inaccuracies in its outputs.**

Users are strongly advised to review the outputs generated by Scribe for accuracy before relying on it for critical tasks or decisions.
{% endhint %}

<details>

<summary><strong>Where can I find the raw transcript from my session?</strong></summary>

1. At [**scribe.gov.sg**](https://scribe.gov.sg/) on your laptop, click into the session of interest

   <figure><img src="/files/q9eHsfqetOs73rkitv2k" alt=""><figcaption></figcaption></figure>
2. At the session's page, click on <img src="/files/jOcwmJyp9eqS9gQtD4Zm" alt="" data-size="line">
3. Select **"View Transcript"**

   <figure><img src="/files/UrmPoPS0y4Wp8NY3g1ds" alt=""><figcaption></figcaption></figure>

</details>

<details>

<summary><strong>My transcript did not label the different speakers (e.g. Speaker 00, Speaker 01). Why?</strong></summary>

Scribe will attempt to distinguish between speakers when possible. However, if the audio quality doesn't allow for clear differentiation of who is speaking, the speaker labels may not appear. Rest assured, that the variation in transcription output doesn't significantly affect the quality of the generated summary.

</details>

<details>

<summary><strong>My transcript was translated to English, even though I recorded it in a different language. Why?</strong></summary>

When non-English languages are spoken, Scribe attempts to translate those parts of the conversation into English while processing the transcript. However, it may occasionally retain some phrases in the original language.

Scribe is not a translation or transcription tool— the transcript is an intermediate step, not the final output. While it may contain imperfections, these generally don't impact the quality of the generated summary.\
\
At the same time, regardless of the language spoken during recording, all summaries generated will be in English.

</details>

<details>

<summary><strong>My transcript has chunks of repeating sentences, and it includes details that the patient and I did not mention during the session. Why?</strong></summary>

Scribe uses advanced audio/language processing techniques, which can sometimes lead to inaccuracies in its outputs. **Users are strongly advised to review the outputs generated by Scribe for accuracy before relying on them for critical tasks or decisions.**

If you notice chunks in your transcript where sentences keep repeating or details seem to be misheard, it's likely due to poor audio quality. In these cases, Scribe may struggle to accurately capture and transcribe that portion of the session. However, this should not significantly affect the quality of the summary generated. **To improve audio quality, we recommend positioning your phone closer to the conversation or articulating words more clearly.**

</details>

<details>

<summary><strong>My session was disrupted so I had to start a new session. I now have two separate transcripts, can I stitch them together?</strong></summary>

No, we don't support stitching different transcripts together.

**However, you could try this workaround:**&#x20;

Generate summaries for both sessions using a similar description (setting the same context) but, modify the headers (what you want Scribe to write about) based on what was discussed in the first and second half of the session.

This way, you can create summaries that cover the entire conversation across both transcripts.

</details>

<details>

<summary><strong>Are the AI-generated transcripts on Scribe fully accurate?</strong></summary>

**No. Scribe uses advanced audio/language processing techniques and will have inaccuracies in its outputs.** Users are strongly advised to review the outputs generated by Scribe for accuracy before relying on it for critical tasks or decision

</details>


---

# 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://guide.scribe.gov.sg/help/faqs/transcripts.md?ask=<question>&goal=<endgoal>
```

`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.