Peer-reviewed research

Automatic Transcription of English and German Qualitative Interviews

Susanne Wollin-Giering et al., Forum: Qualitative Social Research, 25(1), Art. 8, 2024

Read the original

Read on October 17, 2026

What it is: A comparison of nine automatic transcription tools, including Whisper, on one English and one German qualitative interview. It measures data protection, accuracy, time and cost, and reviews how long manual transcription has taken in earlier research.
How much weight it carries: Peer-reviewed and open access, with a stated method. The test used only two interviews at one point in time. The F4x time figures come from that vendor's own study, which the authors report, so they are weaker evidence than the review of earlier research.

Facts taken from this source

In the same F4x study, students needed on average 5.1 times the interview duration to correct an automatic transcript, which the study said saved 70 minutes of correction time per hour of interview.
“for correcting the automatic transcriptions, they needed on average 5.1 times the time. This saved 70 minutes of correction time per hour of interview material” (Section 5.3, Time spent)
Kvale and Brinkmann estimated that manual transcription takes five hours for each hour of interview, a figure Wollin-Giering and colleagues cite in 2024.
“KVALE and BRINKMANN estimated five hours per hour of interview” (Section 5.3, Time spent)
Wollin-Giering and colleagues recommend reviewing the text of any transcript, whatever tool produced it, to ensure accuracy.
“For any type of transcription, we recommend reviewing the text to ensure accuracy.” (Abstract)
Gläser and Laudel found that verbatim transcription took an average of six hours for each hour of interview material in their own research projects, a figure Wollin-Giering and colleagues report in 2024.
“it took an average of six hours to transcribe one hour of interview material for verbatim transcription” (Section 5.3, Time spent)
In a study of more than 200 measurements, students needed on average 6.3 times the interview duration to transcribe an interview manually.
“For manual transcription, the students needed on average 6.3 times the interview duration” (Section 5.3, Time spent)
On the German interview, Whisper reached above 70 percent on the study's word accuracy measure, while Dragon was below 5 percent.
“Dragon's word accuracy measure is below 5%, whereas Whisper reached above 70%.” (Results for the German interview, Figure 3)
Wollin-Giering and colleagues tested nine automatic transcription tools on two interviews and conclude that Whisper performs best overall.
“Based on the analysis, we conclude that Whisper performs best overall and that similar local-automatic transcription tools are likely to become more relevant.” (Abstract)

Pages that rest on this source

Peer-reviewed research

Automatic Transcription of English and German Qualitative Interviews

Susanne Wollin-Giering et al., Forum: Qualitative Social Research, 25(1), Art. 8, 2024

Read the original

Read on October 17, 2026

What it is: A comparison of nine automatic transcription tools, including Whisper, on one English and one German qualitative interview. It measures data protection, accuracy, time and cost, and reviews how long manual transcription has taken in earlier research.
How much weight it carries: Peer-reviewed and open access, with a stated method. The test used only two interviews at one point in time. The F4x time figures come from that vendor's own study, which the authors report, so they are weaker evidence than the review of earlier research.

Facts taken from this source

In the same F4x study, students needed on average 5.1 times the interview duration to correct an automatic transcript, which the study said saved 70 minutes of correction time per hour of interview.
“for correcting the automatic transcriptions, they needed on average 5.1 times the time. This saved 70 minutes of correction time per hour of interview material” (Section 5.3, Time spent)
Kvale and Brinkmann estimated that manual transcription takes five hours for each hour of interview, a figure Wollin-Giering and colleagues cite in 2024.
“KVALE and BRINKMANN estimated five hours per hour of interview” (Section 5.3, Time spent)
Wollin-Giering and colleagues recommend reviewing the text of any transcript, whatever tool produced it, to ensure accuracy.
“For any type of transcription, we recommend reviewing the text to ensure accuracy.” (Abstract)
Gläser and Laudel found that verbatim transcription took an average of six hours for each hour of interview material in their own research projects, a figure Wollin-Giering and colleagues report in 2024.
“it took an average of six hours to transcribe one hour of interview material for verbatim transcription” (Section 5.3, Time spent)
In a study of more than 200 measurements, students needed on average 6.3 times the interview duration to transcribe an interview manually.
“For manual transcription, the students needed on average 6.3 times the interview duration” (Section 5.3, Time spent)
On the German interview, Whisper reached above 70 percent on the study's word accuracy measure, while Dragon was below 5 percent.
“Dragon's word accuracy measure is below 5%, whereas Whisper reached above 70%.” (Results for the German interview, Figure 3)
Wollin-Giering and colleagues tested nine automatic transcription tools on two interviews and conclude that Whisper performs best overall.
“Based on the analysis, we conclude that Whisper performs best overall and that similar local-automatic transcription tools are likely to become more relevant.” (Abstract)