Description

AudioVText converts recorded speech into editable text. It accepts audio and video files as well as links to videos on YouTube, VK Video, Rutube and OK.ru.

Speech recognition in AudioVText is done by AI and covers 99 languages. Russian is the primary language of the service, and recognition is tuned for it.

Every AudioVText transcript is split by speaker and marked with timecodes. An interview reads as a dialogue, and any quote can be located in the recording in seconds. For long conversations AudioVText also writes a short summary of the key points.

Transcripts download as TXT, DOCX or PDF for reading and editing, or as SRT and VTT subtitle files for video. Journalists, researchers, teachers, podcasters and teams that record their calls use AudioVText instead of transcribing by hand.

Uploaded files are stored encrypted, are not shared with third parties, are not used to train models and are deleted automatically. A free tier is available.