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

# Speech to text

> Upload audio, record from the browser, and understand transcription status.

The **Speech to text** page lets you create a new transcript by uploading an audio file or recording directly in the browser.

<Tip>
  Upload files for longer meetings, interviews, and calls. Use browser recording for quick voice notes, short tests, or live dictation.
</Tip>

## Upload a file

<Steps>
  <Step title="Open Speech to text">
    This page creates new transcriptions.
  </Step>

  <Step title="Choose an audio file">
    Drag a file into the upload area or click **Choose file**.
  </Step>

  <Step title="Wait for the duration check">
    The app compares the audio duration with your available transcription time.
  </Step>

  <Step title="Let upload begin">
    If your balance is sufficient, upload starts automatically.
  </Step>
</Steps>

<Info>
  The app upload UI accepts common audio formats: MP3, M4A, WAV, WEBM, OGG, FLAC, and AAC. Video files are not supported in this workflow.
</Info>

## Record from the browser

<Steps>
  <Step title="Click Start recording">
    Your browser will ask for microphone permission.
  </Step>

  <Step title="Allow microphone access">
    Recording cannot start without this permission.
  </Step>

  <Step title="Finish the recording">
    Click **Finish** and the recording uploads automatically.
  </Step>
</Steps>

## Statuses

* **Uploading** — the file is being uploaded.
* **Converting** — the file is being prepared for transcription.
* **Processing / Transcribing** — speech is being converted to text.
* **Transcribed** — the result is ready.
* **Failed** — processing did not complete.

<Warning>
  If the audio duration is longer than your remaining transcription time, the app will ask you to buy more time.
</Warning>