Skip to Main Content

Transcribing Audio and Video (SC)

Transcription Tools

Manually transcribing interviews can be time-consuming, but tools like oTranscribe can help.

Using speech-to-text tools (dictation) can speed up the transcription process without sacrificing too much in way of accuracy. One approach is to listen to your recording (on headphones) and then repeat what you hear to a speech-to-text tool.

Automated transcription is another option. Panopto and Adobe Premiere Pro are two options supported at Swarthmore. You'll need to manually correct the output, often substantially. Automated tools don't handle all voices and terminology equally well. For research, consider whether your IRB approval allows you to share your recordings with an external service and under what terms.

 

Easier Manual Transcribing:

  • oTranscribe - Free web app that speeds up the process of typing up a transcription. Provides keyboard shortcuts and interactive timestamps.

 

Speech-to-Text Tools:

  • Google Docs Voice Typing

  • Built-in voice recognition:

  • Dragon Naturally Speaking

    • Because you train Dragon Naturally Speaking to recognize your voice, this involves some initial set-up time. But it can achieve higher accuracy than other tools as a result.

    • Use this on Windows computers in:

      • Underhill Music & Dance Library Room 105 (inside Lang Music Building)

      • Cornell Science & Engineering Library Room L18

      • McCabe Library Reserve Study Room 007 (requires Student Disability Service approval)

​

Auto-Captioning Video and Audio

Swarthmore ITS provides instruction and support for the following: