> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aseed.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Transcribe records

> Configure transcription settings including language, participants, and speaker names to generate accurate transcripts.

## Overview

Transcripts are the foundation for all reports. Configure transcription settings before generating transcripts to ensure accuracy and proper speaker identification.

## Transcription settings

Before starting transcription, configure these settings in the **Setup** tab of your record:

### Transcript language

Select the language of your interview to improve transcription accuracy. The system supports:

* **Auto detection** - Automatically detects the language
* **Main languages**: English, Russian, Kazakh, Uzbek, Turkmen, Ukrainian, German, French, Spanish, Indonesian
* **Other languages**: 50+ additional languages including Chinese, Japanese, Korean, Arabic, and more

<Tip>
  Selecting the correct language significantly improves transcription accuracy, especially for non-English languages.
</Tip>

<Note>
  In **Auto detection**, multi-language mode is enabled by default. One interview can include two or more languages, and transcription will continue without manual switching.
</Note>

### Number of participants

Specify the number of participants in your interview:

* **Automatic detection** - Let the system detect participants automatically
* **Manual selection** - Choose from 1 to 12 participants

### Participant names

Add known participant names to help the system identify speakers:

1. Enter participant names in the **Participant Name** fields
2. Add multiple participants using the **Add Participant** button
3. Remove participants by clicking the X button next to their name

<Tip>
  Providing participant names helps the system correctly identify speakers throughout the transcript, making reports more accurate.
</Tip>

## How to transcribe records

<Steps>
  <Step title="Open record setup">
    Navigate to a record and open the **Setup** tab.

    <Frame>
      <img src="https://mintlify.s3.us-west-1.amazonaws.com/aseed/images/records-setup-tab-light.png" alt="Record detail page showing Setup tab with transcription settings" className="block dark:hidden" />

      <img src="https://mintlify.s3.us-west-1.amazonaws.com/aseed/images/records-setup-tab-dark.png" alt="Record detail page showing Setup tab with transcription settings" className="hidden dark:block" />
    </Frame>
  </Step>

  <Step title="Activate transcription">
    Toggle the **Activate** switch in the Transcript section to enable transcription.

    <Frame>
      <img src="https://mintlify.s3.us-west-1.amazonaws.com/aseed/images/records-transcription-settings-light.png" alt="Setup tab showing activated transcription with language, participants, and names configured" className="block dark:hidden" />

      <img src="https://mintlify.s3.us-west-1.amazonaws.com/aseed/images/records-transcription-settings-dark.png" alt="Setup tab showing activated transcription with language, participants, and names configured" className="hidden dark:block" />
    </Frame>
  </Step>

  <Step title="Configure language">
    Select the transcript language from the dropdown menu. Choose from Auto detection or specific languages.
  </Step>

  <Step title="Set participant count">
    Choose the number of participants (1-12) or leave it on automatic detection.
  </Step>

  <Step title="Add participant names">
    Enter known participant names in the **Participant Name** fields to improve speaker identification. Click **Add Participant** to add more names.
  </Step>

  <Step title="Start transcription">
    The system automatically starts transcription when settings are configured. Wait for processing to complete. You can monitor progress in the Status column.
  </Step>
</Steps>

## Best practices

<AccordionGroup>
  <Accordion title="Use Auto for mixed-language interviews">
    If respondents switch between languages in one interview, keep language on **Auto detection**.
  </Accordion>

  <Accordion title="Fix speaker names early">
    Fix speaker names early in the process. Correct speaker identification improves report quality.
  </Accordion>

  <Accordion title="Specify number of speakers">
    For interviews with multiple speakers, specify the exact number of participants to help the system distinguish between them.
  </Accordion>
</AccordionGroup>

## Related topics

* [Records page](/interviews/records) - View and manage all records
* [Edit transcripts](/interviews/edit) - Review and correct transcripts after generation