Paste an Apple, Spotify, Buzzsprout, RSS, or YouTube URL. We pull the audio, return a speaker-labelled transcript in about a minute, and hand you DOCX show notes plus SRT/VTT captions for shorts. Your first transcript is free, at any length · instant preview with no signup · packs from $8 for 1,000 minutes, credits never expire.
How it works
No installs, no manual MP3 downloads, no editor — paste a link and the work is done.
Apple Podcasts, Spotify, Buzzsprout, Substack, Podbean, RSS feed, or a YouTube link to your episode upload. We fetch the audio automatically.
Speaker labels are added automatically — host, guest, and any third voices are labelled Speaker 1, Speaker 2, etc. Word-level timestamps let you click to jump back to the audio.
One click for DOCX show notes ready to paste into your CMS. One click for SRT/VTT captions ready for TikTok, Reels, YouTube Shorts, or any web player.
What you can do with the transcript
Whipscribe gives every podcast episode an AI sidebar so you can search, summarize, chat, and export without leaving the page.
Find the exact second a quote was said. Type a phrase — Whipscribe surfaces every matching line with a timestamp you can click.
One click produces a chapter-marked summary, key quotes, and a 280-character social blurb you can paste into your CMS.
Ask “what did the guest say about pricing?” or “list every book mentioned.” The AI answers with quoted timestamps.
TXT, SRT, VTT, DOCX, JSON — every format included at the base price. Hand the DOCX to your editor or the SRT to your shorts queue.
Pricing
Your first episode is free, at any length. After that, episodes are prorated to the second from packs starting at $8 for 1,000 minutes — no monthly commitment, no credit card to start.
FAQ
Paste your episode URL into the box above — Apple, Spotify, Buzzsprout, RSS, or YouTube — and Whipscribe returns a speaker-labelled transcript in about a minute. Preview with no signup; $0.99 opens your first transcript in full, at any length.
Yes. Every voice is labelled automatically — Speaker 1, Speaker 2, and so on — with word-level timestamps you can click to jump back to the audio.
Yes. SRT and VTT are included on every pack — drop the file straight into TikTok, Reels, YouTube Shorts, or any web player.
Yes. The AI sidebar produces a DOCX show-notes block with chapter markers, key quotes, and links mentioned — paste straight into your CMS.
Yes. Paste your RSS URL and we pull the most recent episode's audio — no manual MP3 download required. Apple, Spotify, Buzzsprout, Substack, Podbean, and any standards-compliant RSS work.
Yes. We run open-source Whisper on private infrastructure. Your audio is never sent to OpenAI, Google, or any third-party transcription service, and we never train models on your audio.
MP3, M4A, WAV, FLAC, MP4, MOV, MKV, and most common audio/video containers — or skip the upload and paste a URL.
Instant preview, no signup, no card. A free account keeps your transcripts in one library.