AudioVText

AudioVText turns audio and video recordings into ready-to-use text. Speech recognition runs on AI: Russian is the primary language and the service is tuned for it, while 99 languages are supported in total. Each transcript comes back with timecodes and speaker separation, so a meeting or an interview reads as a dialogue rather than one long block of words. AudioVText also writes a short summary of the conversation. Upload a file or paste a link to a video on YouTube, VK Video, Rutube or OK.ru. The finished text exports to TXT, SRT, VTT, DOCX and PDF — the same result works as subtitles for a video and as a regular document. People use it for interviews, lectures, webinars, meetings and podcasts. Files are stored encrypted, are never shared with third parties, are never used for model training and are deleted automatically. A free tier is available.