Automatically identify who is speaking throughout your podcast. Get a clean, readable transcript formatted as Speaker A / Speaker B, ready to publish, edit, or repurpose.
Transcribe a podcast free →No software to install. Works in your browser.
Drag and drop your MP3, WAV, M4A or any other audio format. Up to 500MB supported.
Toggle "Detect speakers" to automatically identify each voice in your podcast.
Get your full transcript with Speaker A / Speaker B labels. Copy, export as TXT or SRT.
Built for creators, journalists, and content teams.
AI identifies and labels each speaker automatically, no manual tagging needed.
Transcribe podcasts in English, French, Spanish, German, Japanese and 85+ more languages.
Most transcriptions are ready in under 2 minutes, even with speaker detection enabled.
Copy to clipboard, download as TXT, or export as SRT subtitles for video editing.
Generate summaries, key points, blog posts or social captions from your transcript.
Without an account, nothing is stored; signed in, your audio is kept for up to 90 days so you can replay it, then it's automatically deleted.
More transcription tools for audio content
Free to try. No credit card required. Results in seconds.
Create free account →
Dokitscript