Descript instantly turns speech into text in real time. Just start recording and watch our AI speech recognition transcribe your voice—with 95% accuracy—into text that’s ready to edit or export.
Get started →
Create a project in Descript, select record, and choose your microphone input to start a recording session. Or upload a voice file to convert the audio to text.
As you speak into your mic, Descript’s speech-to-text software turns what you say into text in real time. Don’t worry about filler words or mistakes; Descript makes it easy to find and remove those from both the generated text and recorded audio.
Enter Correct mode (press the C key) to edit, apply formatting, highlight sections, and leave comments on your speech-to-text transcript. Filler words will be highlighted, which you can remove by right clicking to remove some or all instances. When ready, export your text as HTML, Markdown, Plain text, Word file, or Rich Text format.
