Descript automatically transcribes speech from your audio into text. This feature enables text-based editing, letting you cut, move, and refine your media directly from the transcript. Transcription also simplifies adding captions, improves accessibility, and makes your content searchable.

This article covers:

• How to transcribe files
• File size limits
• Accuracy and transcription styles

How to transcribe files

You can automatically transcribe a file in Descript in a few ways:

• Add the file to your script: Drag and drop files into the Script editor, or insert files from your Project panel.
• From the Project panel: Click the options menu (⋮) next to a file name, then select Transcribe file.
• When creating a sequence: Import files directly into a sequence; they’ll be transcribed automatically.

Transcription time depends on file length, audio quality, and your internet connection. If your transcript seems stuck, try requesting transcription again.

File size limits

While there’s no strict file size limit, any file longer than 15 hours will fail to transcribe automatically.

Large files may also slow down uploads or cause delays in your project. For best results, split large files into smaller segments before uploading.

Transcription accuracy

Descript uses third-party AI models that are tested and monitored for quality. Accuracy varies with recording quality, accents, background noise, and mic placement. With clear audio, accuracy can reach up to 95%. With challenging audio, accuracy may be lower.

We regularly benchmark major transcription services to maintain high standards. Learn more in How we evaluate transcription accuracy.

Choose a transcription style

By default, Descript selects the transcription style that works best for most content. You can change your transcription provider in App Settings.

Each style is powered by a different AI model with unique strengths—some are faster, some handle punctuation better, and others may perform better for non-English speech or proper nouns.