Skip to main content

Audio Transcription

AI-School offers powerful transcription capabilities to convert audio to text using OpenAI's Whisper model. This advanced AI model is known for its high accuracy and support for multiple languages.

Recording Audio​

There are two ways to submit audio for transcription:

Externally Recorded Audio​

  • Record audio with your phone or other device
  • Upload the audio file to AI-School
  • Supported formats: MP3, WAV, M4A

Direct Recording in AI-School​

  • Use the record button in the interface
  • Start and stop the recording as desired
  • The recording is immediately available for transcription

Transcription Process​

After submitting the audio:

  • OpenAI's Whisper AI model automatically converts speech to text
  • Whisper automatically recognizes the spoken language
  • The text is segmented into speaking turns
  • You can manually assign speakers to text fragments

Exporting​

The completed transcription can be exported to Word or PDF format.

Chatting with Transcriptions​

After exporting, the transcription is automatically available in file management. You can directly:

  • Add the transcription to your prompt
  • Ask questions about the conversation content
  • Let the AI model create analyses and summaries