The AI platform RiverScript provides users with a convenient workflow for converting audio and video into text.

The main functions include media transcription from three types of sources — transcription of audio and video files up to 50 gigabytes in size and up to 8 hours in duration, transcription of the user’s speech recording from the microphone inside the application, as well as Live Recording Transcription on Windows and macOS (regardless of the type of applications launched, that is, RiverScript is capable of capturing the entire system sound of the computer and transcribing it).

RiverScript supports transcription of audio and video in approximately 100 languages, the list of which slightly differs between different models and is described in the languages section. Transcripts can be obtained both as structured text and as subtitles with timecodes. Depending on the type of model, the speaker diarization function is also available.

In addition, RiverScript offers a convenient editor for editing transcripts with the ability to navigate by timecodes and synchronous listening to audio in the built-in player, functions for translating transcripts into 100 languages, transcript storage features, the ability to share transcripts with others, as well as AI Summarize&Ask features (with the help of which one can obtain a summary of the transcript, as well as ask the artificial intelligence any questions about the content of the text).

Unlike other solutions with AI transcription, RiverScript represents not just a tool for local tasks, but a full-fledged workflow for convenient work with media and text, available on different platforms: web application, as well as desktop applications for Windows and macOS. The features of desktop sound capture and transcription available in the desktop client, as well as processing of large files up to 50 gigabytes — these are completely unique features developed by the RiverScript team.