PodText is a professional AI transcription tool for podcasts, audio, and video. Upload MP3, WAV, M4A, MP4, MOV, or WEBM (up to 6 hours / 500MB) for clean, timestamped transcripts in 99+ languages. Edit, search, generate AI show notes, and export to TXT, Markdown, SRT, or VTT. Sign up for 60 minutes of free transcription — no credit card required. Podcast/video links supported: Apple Podcasts, Spotify, RSS, Xiaoyuzhou, iHeart, YouTube (captions).

Hey Product Hunt! 👋

I’m the maker behind PodText.

I built PodText because valuable ideas often get buried inside hour-long podcasts. Finding one quote usually means scrubbing through the timeline—and using most transcription tools means downloading the episode before you can even begin.

PodText takes a link-first approach. Paste an Apple Podcasts, Spotify, iHeart, YouTube, Xiaoyuzhou, or RSS link, and it turns the episode into a timestamped, searchable transcript. You also get AI-generated summaries, chapters, highlights, and key quotes, plus exports in SRT, VTT, TXT, and Markdown. Audio and video uploads are supported too.

The goal is simple: help creators, researchers, and curious listeners turn long-form conversations into knowledge they can search, cite, and reuse.

You can try it with 60 free transcription minutes—no credit card required.

I’d especially love your feedback on:
• Which podcast platform should we support next?
• Which output do you use most: transcripts, summaries, show notes, or subtitles?
• What would make PodText part of your regular workflow?

Thanks for checking it out! 🙌

Can I upload my own audio for transcription?

@ishiguro Yes! You can upload your own audio or video files directly to PodText for transcription. We support common formats like MP3, WAV, MP4, and more. 😊