RiverScript: Turn audio, video, and live recordings into text with AI transcription

Hi everyone, I'm Lex, Founder, and I built RiverScript.

Why I built it I created RiverScript to streamline turning audio and video recordings into accurate text in one easy workflow.

What it does

• Upload or record media including live desktop audio capture
• Transcribe with AI models producing text or timed subtitles
• Edit transcripts with synced audio playback and speaker labeling

I'd love your feedback on How can RiverScript better support heavy file handling and multilingual features in your workflow?