Speaker diarization
AI identifies and labels each speaker automatically — no manual tagging required.
Turn podcasts, interviews, and spaces into speaker-labeled transcripts. Paste a YouTube or X link, upload a file — then view, copy, or export.
AI identifies and labels each speaker automatically — no manual tagging required.
Paste a YouTube URL, an X/Twitter space link, or upload your own audio or video file.
Read in conversation view, copy to clipboard, or download structured JSON for your workflow.
Add a YouTube or X link, or drop in an audio or video file from your device.
AssemblyAI diarizes the audio and returns a transcript with each speaker identified.
Read the conversation view, copy text to clipboard, or download as JSON.
Free to get started. No credit card required.