Home/Learn/Audio and video to text

Audio and video to text

Speech tools are cloud jobs except live dictation, which uses the browser speech service.

Recordings

Audio to text accepts MP3, WAV, M4A, and similar. Video to text pulls speech from a video file. Both give TXT, SRT, and VTT on the dashboard. Podcast transcriber is for multi-speaker shows.

After the transcript

Translation and summarizer take an existing job or upload. Live dictation captures the microphone in the browser; that audio is not stored by ProLampx Tools, though the browser vendor’s speech service may process it.