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

# Speech to Text: Transcribe audio and video instantly

> Monorail AI Transcriber converts spoken words to text using OpenAI Whisper. Upload audio or video files and get accurate transcriptions in seconds.

The Transcriber tool converts spoken audio into accurate text transcriptions using OpenAI's Whisper model. Upload a recording, podcast, meeting, or video file and receive a written transcript within seconds.

## Transcribing audio

<Steps>
  <Step title="Open Transcriber in your dashboard">
    Click **Transcriber** in the sidebar of your Monorail AI dashboard.
  </Step>

  <Step title="Upload your file">
    Select and upload your audio or video file from your device.
  </Step>

  <Step title="Select the source language">
    Choose the spoken language if prompted, or leave it on auto-detect to let the AI identify it automatically.
  </Step>

  <Step title="Click Transcribe">
    Submit your file and wait for the transcript to generate.
  </Step>

  <Step title="Review and copy your transcript">
    Read through the output and copy it for use in your project, document, or workflow.
  </Step>
</Steps>

## Supported use cases

* Meeting and interview transcriptions
* Podcast or video content repurposing
* Lecture or presentation notes
* Accessibility captions for audio content
* Transcribing voice memos

## Tips for accurate transcriptions

* Use clear audio with minimal background noise for the best results.
* Use the Voice Isolator tool to clean up noisy recordings before transcribing — see [Voice Isolator](/tools/voice-isolator) for details.
* Supported formats typically include MP3, MP4, WAV, and M4A.

## Credit usage

Whisper charges by audio duration. 1 credit equals approximately 70 seconds of audio, so a 10-minute recording costs approximately 8.57 credits.

See the [Credits](/credits) page for a full rate breakdown.