PodText
Private podcast, audio, and video transcripts with search, timestamps, AI insights, and exports.
PodText
Turn podcast episodes into searchable text
PodText is a private workspace for turning supported podcast episodes, accessible YouTube captions, and audio or video recordings into searchable transcripts. Review the words with timestamps, search the transcript, and keep the result available for later reference.
Bring a supported source
- Apple Podcasts, Spotify, Xiaoyuzhou, or a public RSS feed (choose one episode when a show or feed returns a list).
- A publicly accessible iHeart episode or direct media link.
- Public YouTube videos or Shorts when an accessible caption track is available.
- Audio and video uploads up to 500 MB and 6 hours.
Read, inspect, and export
- Per-segment timestamps with playback links back to the source audio.
- Full-text search and copyable passages.
- AI summary, chapters, key points, and quotes when generation is available.
- Export as Markdown, TXT, SRT, or VTT.
- Automatic language detection or manual choice across 99+ Whisper-supported languages.
Private by default
Transcriptions belong to the account that created them and are not public pages. New accounts start with a one-time 60-minute allowance without a credit card. Audio made only with signup credits is kept for 7 days after completion; audio processed with subscription or pay-as-you-go credits is kept until the user deletes it. Text, insights, and exports remain available.
Start with one episode
PodText processes one episode per task. Whole-show batch processing, speaker identification, live capture, and collaborative sharing are not part of the current workflow.