Can Claude Listen to Voice Memos? Getting Them into Claude and Claude Code

Claude can't open the recording, so you give it the transcript

Anthropic's list of what you can upload to Claude is documents (PDF, DOCX, CSV, TXT, HTML, ODT, RTF, EPUB, JSON and XLSX) and images (JPEG, PNG, GIF and WebP), and there is no audio format on it, so the .m4a file that Voice Memos saves has nowhere to go. Claude does have voice mode, which Anthropic describes as having "complete spoken conversations with Claude" on mobile, desktop and the web, and Claude Code has /voice for dictating a prompt. Both of those listen to you talking into the microphone right now, and neither of them opens something you recorded earlier.

So what you need is the words out of the recording as text, and once you have that Claude reads it the same way it reads anything else you paste in.

On an iPhone: copy the transcript Voice Memos already made

If you're on iOS 18 or later, Voice Memos transcribes your recordings by itself, and for a single memo you may not need anything else.

1. Open Voice Memos (it's in the Utilities folder) and tap the recording.
2. Tap the More Actions button and choose Copy Transcript. If you only want part of it, choose View Transcript instead and select the bit you want.
3. Open the Claude app, start a conversation, paste it in, and say what you want done with it.

What decides whether this works for you is language. Apple's transcription needs an iPhone 12 or later and covers English, Spanish, Portuguese, Italian, French, German, Japanese, Korean and Simplified and Traditional Chinese, and Apple says it isn't available in every country or region either. Record in Swedish, Dutch, Polish or Finnish and there is no transcript to copy. Claude Code's dictation draws the line in a different place, with Swedish, Dutch and Polish among its twenty languages, and Finnish is in neither list, so which of Apple's and Anthropic's tools helps you at all depends a lot on where you live.

On a Mac: transcribe locally and keep the text

On a Mac, My Transcriber does the transcribing. It runs Whisper on the Mac itself, so the audio never leaves the machine, and it picks up the Voice Memos that sync over iCloud from your iPhone and Watch as well as the ones you record on the Mac. Each one becomes a markdown file in a folder, organised by date, in whatever language you spoke, because Whisper works out the language per recording across 99+ of them.

From there you paste the text into Claude in the same way, or, if you use Claude Code, you don't paste anything and it reads the folder. That second case is where I spend most of my day, and it changes how I use voice with Claude altogether.

Using voice with Claude Code: record a memo instead of dictating

Most of what I hand Claude Code started out as speech, and almost none of it goes through Claude's own dictation. I hit record on the Mac, talk for as long as I want, stop, and a few seconds later the transcript is sitting there for me to paste in. That is the loop, and it is for work I am doing right now with Claude Code open in front of me.

I did expect to be using /voice for this and I am not, which took me a while to admit.

Why the built-in dictation didn't stick

Claude Code's /voice is real dictation and it works: hold space, talk, and your words appear in the prompt as you speak. I still use it, but only for the shortest things, a line or two where I would otherwise be typing a sentence. Past that it stops being worth it. It takes longer than you expect, it mishears enough that I am editing the result instead of reading it, and I cannot predict which of those two I am going to get.

Some of that is visible in how it is built. Your audio goes to Anthropic's servers rather than being handled on your machine, and in tap mode the recording stops on its own after two minutes or after fifteen seconds of silence. Two minutes is a reasonable ceiling for a prompt and nowhere near enough for thinking something through.

Then there is language, and this one took me a while to work out because it looks like the dictation simply can't do Swedish. It can. Swedish is one of the twenty it supports. What it doesn't do is detect anything: dictation uses whatever language you have configured, and if you haven't configured one it assumes English and transcribes your Swedish as though it were English, which produces the sort of output that makes you conclude the feature is broken. Anthropic's own troubleshooting page lists this under transcription coming back garbled or in the wrong language.

You can set it, and here's the catch: it's the same setting that controls what language Claude replies in. So dictating in Swedish means being answered in Swedish, and if you go back and forth between languages during a day, as I do, you are changing a config setting each time rather than just talking. In practice everybody leaves it on English and puts up with the results.

Whisper detects the language itself, per recording, with nothing to configure and no effect on anything else. Finnish comes back Finnish, and the memos that wander between two languages halfway through, which most of mine do, come back intact. Finnish also isn't among the twenty at all, which where I live settles it.

The loop I actually use

I start a voice memo on the Mac, right there at the desk, in the middle of working. Then I talk for as long as it takes, which is usually a few minutes and sometimes twenty, while I page through the code or stop to read a diff or lose my thread completely and start the sentence again. Nothing is counting down and nothing needs to stay in the foreground. When I stop, My Transcriber transcribes it on the Mac and the text is there almost immediately, and I paste it into Claude Code.

"Almost immediately" is the part that makes this work rather than a nice idea. Whisper on an Apple Silicon Mac runs at about thirty times faster than real time with Metal, so ten minutes of talking comes back in around eighteen seconds and an hour takes under two minutes. Wait long enough to reach for your coffee and it's done.

The other one, which is genuinely away from the desk

Separately from all that, I record memos on my Apple Watch or my phone — my own thoughts, a conversation, a meeting I'm sitting in. Those sync over iCloud, get transcribed on the Mac whenever they land, and are waiting as markdown by the time I sit down. It's the same mechanism and a different habit, and it isn't the hands-on Claude Code loop above. It's how the thinking I did on a walk ends up somewhere I can use it.

Then let Claude Code go and find them

Pasting is fine and I do it constantly, but you can skip it. My Transcriber ships an MCP server, so Claude Code can query the voice memo index directly. I say "I talked about this in one of my recent voice memos, go and read it," and it does. The app sets that up on first launch by writing an .mcp.json into your data folder along with a bundled skill, so running claude from that folder picks it up.

It works the other way round too. Claude Code can put things into the library rather than only reading from it, so "download the recording of yesterday's meeting and transcribe it" runs Whisper on your Mac and the recording turns up alongside your voice memos, searchable, in the app. Ask Claude Code to transcribe something on a machine without My Transcriber and it will still have a go — usually by installing Whisper itself and improvising a script around it, which does work and leaves you with a stray text file that nothing else knows about.

Four things that make this work better

Don't bother introducing it. I went through my own library while writing this and almost none of my memos say what they're about — they open mid-thought, halfway into a sentence, the way you actually start talking when something occurs to you. It doesn't matter, because the whole transcript is searchable and describing the content is enough to find it later. A spoken subject line would be a chore you'd give up on by the third memo.

Don't perform, either. It's going to a language model, not to a reader, so false starts and repetition and changing your mind halfway through a sentence are all fine. The messy version is often the useful one, because the reasoning is in there rather than just the conclusion.

Type the short ones. The split that matters isn't voice against typing, it's short against long. A one-line instruction is quicker typed than spoken, and that's the job dictation is for if you want it. Everything past a couple of sentences is faster recorded, and gets more accurate rather than less as it goes on.

Let them pile up. A single transcript is a note. A year of them is context you can ask questions across, which is a different thing entirely, and it costs nothing to keep because they're small text files sitting in a folder you already back up.

Setting it up

1. Install My Transcriber and grant Full Disk Access, which is what lets it read Voice Memos synced from iCloud.
2. Next time you're about to type a long thing at Claude Code, record a voice memo on the Mac instead and talk it through. Stop when you're finished; the transcript appears in your folder within seconds.
3. Paste it in. That's the loop, and it's most of what this is for.
4. Later, once memos have accumulated: run claude from that folder and ask it about them directly, and record on your phone or Watch when you're away from the desk.

Common questions

Can Claude listen to voice memos?

Not the recording itself. Claude's file uploads take documents and images with no audio format among them, and voice mode is for talking to Claude live rather than playing it something you recorded earlier. Get a transcript of the memo first, from Voice Memos on an iPhone or locally on a Mac, and Claude reads the text like anything else you give it.

Can I upload a voice memo to Claude?

You can give it the transcript, not the .m4a file. On iOS 18 or later, Voice Memos has Copy Transcript in a recording's More Actions menu, in ten languages, and you paste that into the Claude app. For other languages, or to keep every transcript as a file Claude Code can read, My Transcriber writes each memo to a markdown file on your Mac.

Doesn't Claude Code's voice mode already cover this?

For short prompts, yes. Past a couple of sentences it stops being worth it — it takes longer than you expect, it mishears often enough that you end up editing rather than reading, and in tap mode recording stops after two minutes or fifteen seconds of silence. A voice memo has no ceiling, doesn't need anything in the foreground, and comes back more reliable rather than less as it gets longer.

Which languages does Claude's dictation handle?

Twenty, and it does not detect which one you're speaking: Czech, Danish, Dutch, English, French, German, Greek, Hindi, Indonesian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Russian, Spanish, Swedish, Turkish and Ukrainian. Dictation uses whichever language you have configured and assumes English if you haven't set one, so speaking Swedish at a default install gets you Swedish transcribed as English. You can change it, but it's the same setting that controls what language Claude replies in. Whisper, which My Transcriber runs on your Mac, detects the language per recording across 99+ of them with nothing to configure.

Can Claude transcribe an audio file?

Claude in a chat window can't — the upload list is documents and images, with no audio format on it. Claude Code is a different story, because it can run things: ask it to transcribe a recording and it will go and find a way, usually by installing Whisper itself and improvising a script. With My Transcriber installed it has a proper one. The app writes a transcribe skill and the CLI path into your folder, so "download the recording of yesterday's meeting and transcribe it" runs on-device, and the recording and its transcript land in your library alongside your voice memos, searchable in the app.

Does the transcription happen in the cloud?

Not with My Transcriber. Whisper runs on your Mac with Metal GPU acceleration and the audio never leaves the machine. Claude Code's dictation is documented as streaming your recorded audio to Anthropic's servers for transcription.

How long can a voice memo be, and how long does transcribing take?

Long enough that length stops being something you think about. Whisper runs at roughly thirty times faster than real time on an Apple Silicon Mac with Metal, so ten minutes of talking comes back in about eighteen seconds and an hour takes under two minutes. Nothing stops the recording while you make it, and Claude Code can read the transcript as a file rather than you pasting it into a chat box.