Podcast Transcription

Transcribe Podcasts to Text
with Speaker Labels

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
Supports MP3, WAV, M4A · 90+ languages · No installation required
Sample output, Speaker Detection
A
Welcome back to the show! Today we're talking about content creation at scale.
0:00-0:06
B
Thanks for having me. I've been doing this for 5 years and the game has completely changed.
0:07-0:13
A
Completely. Let's start with short-form video, what's your approach?
0:14-0:19
B
My approach is always to start with the transcript. Once you have the words, everything else follows.
0:20-0:27
How it works

Transcribe your podcast in 3 steps

No software to install. Works in your browser.

1

Upload your audio

Drag and drop your MP3, WAV, M4A or any other audio format. Up to 500MB supported.

2

Enable speaker detection

Toggle "Detect speakers" to automatically identify each voice in your podcast.

3

Copy or download

Get your full transcript with Speaker A / Speaker B labels. Copy, export as TXT or SRT.

Features

Everything podcasters need

Built for creators, journalists, and content teams.

Automatic speaker detection

AI identifies and labels each speaker automatically, no manual tagging needed.

90+ languages

Transcribe podcasts in English, French, Spanish, German, Japanese and 85+ more languages.

Fast results

Most transcriptions are ready in under 2 minutes, even with speaker detection enabled.

Multiple export formats

Copy to clipboard, download as TXT, or export as SRT subtitles for video editing.

AI-powered summaries

Generate summaries, key points, blog posts or social captions from your transcript.

Translate the transcript

Get the text in another language in one click, ready to reuse or subtitle.

FAQ

Common questions

Can Dokitscript transcribe podcasts with multiple speakers?
Yes. The Pro and Business plans include automatic speaker diarization, each speaker is automatically labelled as Speaker A, Speaker B, etc. throughout the transcript.
What audio formats are supported?
MP3, WAV, M4A, OGG, WebM, AAC, FLAC and MP4. Maximum file size is 500MB.
How long can my podcast be?
Free accounts support up to 120 seconds. Starter up to 10 minutes. Pro up to 120 minutes. Business up to 300 minutes per transcription.
Is there a free trial?
Yes. Create a free account and get 5 transcriptions per month, no credit card required. Speaker detection is available from the Pro plan.

Related Tools

More transcription tools for audio content

Lecture Transcription Speaker Diarization Audio Transcription SRT Generator

Start transcribing your podcast today

Free to try. No credit card required. Results in seconds.

Create free account