How to transcribe a podcast episode on a Mac for free, and turn it into show notes
By Ryleigh Newman · Published
To transcribe a podcast on a Mac for free, export the finished episode from your editor as an M4A or WAV file, drop it on the Transcribe a file card in YapToText, and copy the text, transcribed on your Mac with Whisper and never uploaded. The same app then turns that transcript into a first draft of your show notes.
I built YapToText because my hands make typing difficult, and writing up an hour of conversation by hand is exactly the typing I avoid. It is free, with no account and no minute cap, and it needs an Apple silicon Mac with macOS 14 or later. One thing up front: what comes back is the words, with no timestamps, chapters or speaker labels. If you need a caption file for a podcast app, the section on caption and transcript files says where to get one.
Download for free. No account, nothing locked, macOS 14 or later on Apple silicon. Source on GitHub.
On this page: 10 sections
Steps
- Export the finished episode from your editor as one M4A or WAV file.
- Add guest, sponsor and show names to a dictionary on YapToText's Dictionaries page.
- On the Utility page, pick Raw Transcription in the Transcribe a file card's mode menu.
- Drop the episode on the card, or click Choose File, then click Copy to keep the raw transcript.
- Click Send below, pick Note in the Transform text card and press Transform for a show notes draft.
- Check the notes against the raw transcript, then copy them into your show notes.
Export the episode as one audio file
YapToText works on a file, not on your editing project, so the first step happens in whatever app you edit in. Export the finished episode as an M4A or WAV file, and that file is what you transcribe.
Step 1: Export the mix
- You: In your editor, export the finished episode as one audio file, M4A or WAV. Every editor names this a little differently, so look in its File or Export menu.
- YapToText: Nothing yet. It reads files of almost any kind, recognized by their content rather than their extension, including M4A, WAV, AIFF, CAF, FLAC, MP3, MP4 and MOV.
- Check: The exported file plays on your Mac from start to finish.
Step 2: Leave the music out if you can
- You: If your editor can export a version without the intro and outro music, or you can trim them off, do that for the transcript copy.
- YapToText: Transcribes whatever is in the file. Long stretches of music give the speech model nothing to transcribe and can come out as stray words. YapToText compresses long pauses and removes repetition loops and pleasantries hallucinated from silence, but trimming the music is still the safest start.
- Check: The file starts and ends with someone talking.
Two kinds of episode need a word of their own:
- A video podcast. Drop the MP4 or MOV as it is, and YapToText transcribes the soundtrack. If it will not open, QuickTime Player can save the sound alone: choose File, Export As, Audio Only, which Apple says saves an MPEG 4 audio file with an AAC track. The guide to turning a video into text has more.
- Separate tracks. If each host and guest was recorded on their own track, you can export each one and transcribe it on its own, which gives you one person's words per transcript. YapToText adds no timestamps, so it cannot weave the tracks back into one conversation. For the full mix, the interview transcription guide shows how to put names on each turn by hand.
Teach it your guests' and sponsors' names
A podcast is full of words a speech model has never heard: your show's name, your guest's name, the guest's company, and the sponsor you read an ad for halfway through. Add this episode's names before you drop the file, not after.
On the Dictionaries page, each entry pairs what the app hears, in Heard, with the spelling you want, in Replace with. The Replace with side is also handed to Whisper as words to listen for, and your dictionaries apply to file transcription as well as dictation.
Dictionary entry: A guest whose name is spelled nothing like it sounds.
Heard: neve
Replace with: NiamhWhat happens: Every neve in the transcript is written Niamh, and Niamh is handed to Whisper as a word to listen for.
- One dictionary for the show. Press New Dictionary and name it after the podcast. Each dictionary has its own switch, so you can keep a season's worth of guests without deleting anything.
- Keep the list short. The words handed to Whisper fit in a budget of about 200 characters, with your dictionary terms first. Keep only the dictionaries you need switched on; the budget is about 200 characters, with your dictionary terms first.
- Match what it heard. If a name still comes out wrong, put the spelling it actually wrote in Heard and run the file again, or press Generate variations on the entry. The Dictionaries guide covers Whole word, Case and order.
- Set the language. The Language picker on the AI Models page starts on your Mac's system language. For a show in another language, choose it, or Auto-detect language. The language guide lists all 29.

Transcribe the episode
The transcript comes from one card on YapToText's Utility page, Transcribe a file, using the same Whisper model that handles live dictation, on your Mac. YapToText is free on the Mac App Store. Pick Raw Transcription, drop the episode, and copy the text.
Step 1: Pick Raw Transcription
- You: Open the Utility page. In the Transcribe a file card's mode menu, pick Raw Transcription.
- YapToText: Uses that mode for the file. Raw Transcription is literal speech to text with basic punctuation, and no AI rewrites the words.
- Check: The menu says Raw Transcription. A faithful transcript first means you always have the version nothing touched.
Step 2: Drop the episode
- You: Drag the exported file onto the card, or click Choose File and pick it.
- YapToText: Transcribes it on your Mac. A recording over 4 minutes is cut at quiet moments into pieces of about 2 minutes.
- Check: The card says it is transcribing your file. If it shows an error, the ladder further down has the fixes.
Step 3: Keep the raw transcript
- You: Click Copy and paste the text into a document for this episode, before you do anything else with it.
- YapToText: Hands over plain text, with no speaker labels or timestamps.
- Check: The whole episode is saved somewhere outside the card.
A file has no minute cap and nothing is metered, so a two-hour episode simply takes longer, on your Mac's own chip. The Utility card keeps nothing once you clear it. If you would rather have a record, use Transcribe file in the menu bar panel instead: it uses your current mode, copies the text to your clipboard and files it in History under the file's name, where Export Text saves it as a .txt file. History deletes entries older than 30 days by default, so export the ones you want to keep.
Write show notes from the transcript
Show notes are the part listeners actually read, and they are where a transcript pays for itself. YapToText has three ways to turn the raw text into a draft, all on your Mac. Transcribe raw, then shape a copy into notes, and keep the two apart.
Step 1: Send the transcript down
- You: In the Transcribe a file card, click Send below.
- YapToText: Passes the text to the next card, Transform text.
- Check: The transcript is in the Transform text card.
Step 2: Pick Note and press Transform
- You: In Transform text, pick Note and press Transform.
- YapToText: Rewrites it with the cleanup model as short headings and bullets, with action items pulled into a list and nothing added that was not said.
- Check: Read every name, number and sponsor code against the raw transcript before you copy it out.
Below Transform text, the AI action on text card runs a saved AI Action on any text. Paste the transcript or a section of it, and run Summarize, Bullet Points or Make Concise on it. For a transcript you want to post as readable text, Transform text with Clean Up removes filler words and false starts, writes spoken web addresses in proper form, and never deletes, shortens or summarizes a sentence.
If you write the same shape of show notes every week, make a mode for it. On the Modes page, right-click Note and choose Duplicate, then write what you want in the Instructions box of the AI cleanup card, and test it with Preview with AI in the Try it out card. Transform text offers every mode with AI cleanup, so your new mode shows up there.
Mode instructions: An example for a weekly show.
Turn this podcast transcript into show notes: two sentences on what the episode is about, then a bullet list of the topics in the order they come up. Use only what was said. Do not add links, times or anything that is not in the transcript.What happens: The cleanup model follows these instructions each time you run that mode in Transform text, on your Mac.
- A section at a time. The cleanup model is small, and I have not tested how it handles a full hour of transcript in one pass. Paste one segment at a time into Transform text and put the results together.
- Quotes stay raw. For a pull quote or a social post, copy the words from the raw transcript and check them against the audio. A rewrite makes readable notes and a changed quote.
- Episode description. If you would rather talk it out, YapToText dictates into any app with one key, and the guide to dictation for writers covers drafting by voice.
The modes guide explains what each mode does and how to edit its instructions, and the Utility page guide covers all four cards.

Caption and transcript files need another tool
Some podcast apps show a transcript next to the episode, and that transcript is a timed file, not plain text. YapToText does not make one. YapToText gives you the text for show notes; a timed transcript file comes from somewhere else.
Checked October 5, 2026, on Apple Podcasts for Creators, and October 3, 2026, on macwhisper.com. Features change, so check before you rely on one.
| Apple Podcasts | MacWhisper, free version | YapToText | |
|---|---|---|---|
| What it does | Makes transcripts automatically for new episodes, shortly after they are published | Transcribes a file on your Mac with local models | Transcribes a file on your Mac |
| What you get | A transcript in Apple Podcasts, marked Automatically generated | Text, plus .srt and .vtt subtitles | Plain text to copy or insert |
| Your own transcript file | Accepted as VTT or SRT, through your RSS feed, or in Apple Podcasts Connect for subscriber episodes | Exports .srt and .vtt | Makes no VTT or SRT file |
| Speaker labels | Not covered here | On Pro, with speaker recognition | No |
| Price | Not covered here | Free; Pro €64 once | Free, no paid tier |
Apple's guide for creators says that if you provide your own transcripts, it takes them through the transcript tag in your RSS feed, so check whether your hosting provider supports that, and it lists the languages it accepts: English, Danish, Dutch, Finnish, French, German, Italian, Norwegian, Portuguese, Spanish and Swedish. For a VTT or SRT file made on your Mac, MacWhisper's free version exports both, and the MacWhisper comparison covers what else it does. YapToText's transcript is for everything around the episode: the show notes, the episode page, a newsletter, and a searchable archive of what you have said on the show.
If the transcript comes back wrong
Start with the file, then the settings. Most bad podcast transcripts come from music, silence or the wrong language. Climb this ladder, smallest step first:
- Play the file. If the card says no speech was found, listen to it. An export with the voice tracks muted gives any speech model nothing to work with.
- Trim the music. If words appear over the intro music, cut the music and run it again. Cut the music and long silences from the start and end and run it again. The guide to Whisper hallucinations explains why it happens.
- Look at the raw words. Run it with Raw Transcription to see what the model heard before any cleanup.
- Check the language. A show in another language needs that language, or Auto-detect, on the AI Models page.
- Export again. If the card shows an error, export the episode again as M4A or WAV and drop that instead.
- Use a bigger model. Download one from the Dictation Model Library on the AI Models page and run the file again. A model download is the only network use the app starts.
The guide to transcribing any audio file on a Mac lists every format YapToText reads.

What it cannot do
- Timestamps and chapters. It adds no timecodes, so it cannot mark chapters or say where in the episode a topic starts.
- Speaker labels. It does not say who is talking, so nothing marks which host is talking.
- Subtitles and transcript files. It exports no SRT or VTT. MacWhisper's free version does.
- Links and feeds. It needs the audio file on your Mac. It cannot open a podcast link or an RSS feed; MacWhisper Pro lists podcast and YouTube link transcription.
- Batches. It takes one file at a time, so a back catalog goes through one episode at a time.
- Recording. It does not record calls or system audio. A remote interview is recorded by your recording tool, and YapToText reads the file afterwards.
- Translation as it transcribes. It writes the episode in the language it was spoken. To translate afterwards, run Translate to English, one of the built-in AI Actions, or select the text and ask Quick Edit for another language.
- Some Macs and builds. It needs macOS 14 or later on Apple silicon, and nothing is claimed for Intel Macs. The Homebrew build ships without models, so download a speech model on the AI Models page first.
It gives you the words of the episode, not who said them or when.
The short version
- Export. The finished episode as one M4A or WAV file, with the music trimmed if you can.
- Transcribe. Add guest and sponsor names to a dictionary, pick Raw Transcription, and drop the file on the Transcribe a file card.
- Show notes. Send the text below to Transform text and pick Note, or run Summarize or Bullet Points, then check it against the raw transcript.
- Caption files. Use MacWhisper's free .srt and .vtt export, or Apple Podcasts' own transcript.
The episode goes in, the words and a draft of the show notes come out, and nothing leaves your Mac.
If an episode will not transcribe, press Copy Diagnostics in Settings, About and open an issue on GitHub with the file type. Every one gets read.
Download for free. No account, nothing locked, macOS 14 or later on Apple silicon. Source on GitHub.
Related
Sources
- https://podcasters.apple.com/support/5316-transcripts-on-apple-podcasts (checked 2026-10-05)
- https://www.macwhisper.com (checked 2026-10-03)
- https://support.apple.com/guide/quicktime-player/export-movies-qtp20e395859/mac (checked 2026-10-03)
- https://apps.apple.com/us/app/yaptotext/id6786382289 (checked 2026-10-03)
Questions
How do I transcribe a podcast for free on a Mac?
Export the episode from your editor as an M4A or WAV file, then drop it on the Transcribe a file card on YapToText's Utility page with Raw Transcription picked, and copy the text. It is free, transcribes on your Mac, and needs macOS 14 or later on Apple silicon.
Can I transcribe a podcast episode offline?
Yes. The App Store build of YapToText ships with its speech model and transcribes on your Mac with Wi-Fi off. The only network use it starts is a model download you choose.
How do I turn a podcast transcript into show notes?
In YapToText, click Send below on the transcript, pick Note in the Transform text card and press Transform, or run Summarize or Bullet Points in the AI action card. Check names and numbers against the raw transcript before you publish.
Does Apple Podcasts make transcripts automatically?
Apple's guide for creators says transcripts become available automatically for new episodes shortly after they are published. If you provide your own instead, Apple takes it as a VTT or SRT file.
Can YapToText make an SRT or VTT transcript for my podcast?
No. It gives plain text with no timestamps. MacWhisper's free version exports .srt and .vtt files on your Mac.
Will the transcript show which host is talking?
No. YapToText adds no speaker labels. If each person was recorded on their own track, transcribe each track separately to get one person's words per transcript.