Andreas Muller presented at MAXDAYS 2025 a session on the “Nuts and Bolts of Transcription.” As I am preparing for focus groups, this is of interest. Muller noted that after an interview, the audio or video are often transcribed before analyzing. Muller started by creating a new MAXQDA 2024 project. Importing an interview results in a prompt with several options: import the file only, link to an existing transcript, or transcribe with AI. Muller reminded us that the audio is saved as an external file: MAXQDA keeps the file in the original location and makes a copy in the external files folder. Muller started the automatic transcription by clicking on the file and selecting transcription. This system is based on purchasing credits. Muller used the manual transcription option. This allows you to type and transcribe, providing pausing and timestamps. Muller spoke about the shortcut keys for manual transcription and the AI transcription service. There are various supported languages and file formats. The maximum file size is 1 Gb. Also, Muller noted that there is an English/Spanish mix option for transcription. The AI also indicates when there are pauses and music. The speakers are identified, and time stamps are provided. With the edit mode activated, you can make corrections. Muller suggested conducting interviews using standard language (avoid too much jargon) and try to obtain high-quality audio. You can include vocabulary to help AI transcription. Focus group transcripts have more than two speakers. MAXQDA can identify individual speakers. Focus group transcripts have specialized analysis tools, noted Muller. I will have to try that!
