Voxt

Voxt is an iOS app for iPhone and iPad that turns spoken recordings and video files into text. You can record a lecture, meeting, interview or voice note, or import an existing file, and the app transcribes it and detects the spoken language. A Quick mode gives free, real-time speech to text on the device in 21 languages, aimed at dictation and short notes, while longer recordings go through cloud transcription.

Imports cover common audio formats such as MP3, M4A, WAV and FLAC and video formats such as MP4, MOV and MKV. From any transcript, one tap produces a short summary or bullet-point notes, a translation into more than 100 languages, or a chat where questions are answered from the transcript. The Pro tier adds summaries of online videos from a pasted link (the video needs captions) and beta meeting notes with decisions and action items. Transcripts stay in a searchable history that can be edited, copied or shared.

The app is pitched at students recording lectures, professionals keeping meeting notes, journalists and researchers transcribing interviews, and creators turning video into scripts or show notes. Usage is counted in minutes of audio, and AI actions such as a summary or chat message also draw from that balance.