I made a CLI that turns any podcast or YouTube video into clean Markdown transcripts (speaker labels + timestamps)
Open-source tool uses ElevenLabs for speaker diarization and automatic timestamping.
Deep Dive
Developer Timf34 built Podscript, a command-line interface tool that transforms audio and video content into structured Markdown transcripts. It uses ElevenLabs' API for high-quality speaker diarization (identifying who is speaking) and automatically inserts speaker labels and timestamps. Users can install it via 'pip install podscript' to quickly generate clean, formatted transcripts from podcasts or YouTube videos for documentation, content repurposing, or accessibility.
Why It Matters
Automates a tedious manual process, saving hours for content creators, researchers, and journalists who need accurate transcripts.