Start free

Voice memo to text.iPhone, Android, any app.

Drop the voice memo off your phone. We read M4A, AAC, and MP3 straight from iPhone Voice Memos, Android Recorder, or any dictation app — no conversion, no desktop sync.

Drop a file, or pick one

MP3 · WAV · M4A · MP4 · MOV · MKV · OGG · OPUS · FLAC · WEBM — up to 100 MB anonymously

Paste a link, we’ll fetch the audio

YouTube · TikTok · Vimeo · Twitter · SoundCloud · Spotify · 50+ more

Record straight from your browser

Sign up takes 30 seconds — recording opens right after, in the dashboard.

No card required~90s per 60-min fileSRT · VTT · DOCX · TXTFiles auto-deleted in 24h

↓ Watch what comes out

Phone memo in. Searchable transcript out.

Voice memos are usually one person thinking out loud with imperfect mic placement. We tune for solo dictation by default, and flip on diarization when we hear a second voice.

iPhone Voice Memos · M4AREC Solo dictation · 4:12
auto-detected en-US44.1 kHz mono · AAC 64 kbps
~90s
Transcript · streaming95% accuracy
S1

Idea for the Tuesday piece — open with the FOIA response, not the lawsuit.

S1

The 217-page PDF is the lede. Quote the redacted paragraph on page 84.

S1

Then pivot to the council vote. Need to call Reyes back before 5pm.

S1

Working title — 'What the redactions tell us.' Park it, come back tomorrow.

95% on close-mic dictationDOCX · TXT · SRT · JSON

↓ This is the dashboard

This is what loads when the job finishes.

Same layout as the real dashboard — Summary, full Transcript, Speakers tab, Exports. Key points and action items extracted automatically. Auto-tags on every job.

Try it on your own file — it's free

Three real options · honest comparison

Apple's built-in. Otter mobile. Or us.

iOS 18 added transcription inside Voice Memos. Otter has a mobile recorder. Both work — until the memo is long, multilingual, or you want a file you can actually export. We start from whatever the recording app saved.

Option 01

Apple Voice Memos transcript

Built into iOS 18+ Voice Memos. Only on recent iPhones, English-leaning, no export.

RequiresiPhone 12+ on iOS 18
Speaker labelsNo
LanguagesEN, ES, FR, DE, JA, ZH
ExportCopy/paste only
Old memosRe-process one at a time
CostFree with hardware
Best forSolo iPhone users on a new device who only need to skim one memo at a time.
Option 02

Transcription.Solutions

Share any memo from iOS or Android. Get DOCX, SRT, TXT — and speaker labels when there are two voices.

RequiresNothing — share sheet works
Speaker labelsYes (Pro / Business)
Languages99, auto-detected
ExportDOCX · SRT · TXT · JSON
Old memosBatch upload from Files
Cost · per min$0.03
Best forAnyone with a backlog of memos, mixed devices, non-English dictation, or memos that need to land in Word or a CMS.
Option 03

Otter mobile / Google Recorder

Record in their app or it doesn't work. Won't read memos you already captured elsewhere.

RequiresRecording inside their app
Speaker labelsAcoustic, EN-tuned
LanguagesEN mostly · Google adds a few
Existing M4A filesOtter free: no upload
Monthly cap300 min free (Otter)
Cost$17/mo (Otter Pro)
Best forPeople starting from zero who don't mind switching to a new recorder app for every note.

Pricing and feature flags accurate as of May 2026. Apple's Voice Memos transcription rolled out with iOS 18 in late 2024.

Specific to voice memos

Three things that quietly wreck phone-recorded memos.

None of this is about the AI. It's about where the phone was when you hit record.

What goes wrong

  1. 1Pocket recordings. Fabric on the mic creates a low-frequency rumble that masks consonants. The model hears 'sh' where you said 's'.
  2. 2Plosives from close-talking. Holding the phone like a mic puts P and B pops directly on the diaphragm. Words right after the pop get eaten.
  3. 3Long silences while thinking. Generic recognizers hallucinate filler ('you know', 'I mean') into 3+ second gaps. Reads fine, isn't what you said.

What to flip here

  1. 1We auto-detect mono fabric-noise memos and apply a high-pass filter before recognition. You can also flip 'Pocket recording' on the job form.
  2. 2Hold the phone at the side of your mouth, not in front, or use earbuds with a mic. Then set Speaker model: Solo dictation — it skips diarization entirely.
  3. 3Turn on Suppress hallucinations in silence and the model emits nothing during long gaps instead of inventing speech. Your pauses stay pauses.

Recommended job settings for voice memos

Drop an M4A or AAC and these flip on automatically. Override per-job from the form.

Speaker model
Solo dictation (auto-switch if 2nd voice)
Diarization
Off by default · on for interviews
Language
Auto-detect · 99 supported
Filler words
Removed by default
Silence handling
Suppress hallucinations in gaps
Export
DOCX · TXT · timestamped SRT

Accuracy · real-world numbers

95%+ on close-mic dictation. Down to 78% in your jacket pocket.

Voice memos are mostly a mic-placement problem, not an audio-quality problem. Phone mics are good — fabric, wind, and a pocket are not. Numbers below come from real customer memos, not lab files.

95%+
Close-mic solo dictation

Phone held 6-12 inches from your face, quiet room. iPhone or Pixel main mic. Cleanest case — most journalists' and writers' memos land here.

92%
Solo memo, light room noise

Café hum, HVAC, a passing siren. Phone on the desk in front of you. Filler words and the occasional 'um' may slip through unless you remove them.

87%
Two-person captured interview

Phone between you on a coffee table. Acoustic diarization separates voices, though crosstalk and similar pitches sometimes merge — budget a 2-min cleanup.

78%
Pocket or walking-outdoor memo

Fabric rubbing the mic, wind, traffic. Words are usually recoverable for note-taking but proper nouns and numbers drop fastest. Worst case in our data.

Common questions

8 things people ask about voice memo transcription.

01Do I need to convert M4A from iPhone Voice Memos first?+
No. M4A uploads directly — same for Android's AAC and MP3. We read the container natively and don't re-encode. Just tap Share → Transcription.Solutions from the Voice Memos app, or drag the file from Finder.
02iOS 18 already transcribes Voice Memos — why use you?+
Apple's transcript stays inside the app — no DOCX, no SRT, no batch export. It's also English-leaning and only on iPhone 12 and newer. If you want a file you can edit, send to a client, or paste into a CMS, you need an external tool.
03Can you handle a 4-hour memo? I forgot to stop recording.+
Yes. Max file is 5 GB and max duration is 10 hours per job. A 4-hour mono M4A is roughly 200 MB and processes in about 12-15 minutes on the standard tier.
04I recorded an interview on my phone — will speaker labels work?+
Yes, on Pro and Business plans. Two voices on a single mic are harder than separate channels, so expect 85-90% diarization accuracy if you were both close to the phone. Budget a quick rename pass on the speaker chips.
05Does the share sheet work from the iOS Voice Memos app?+
Yes. Open the memo, tap Share, pick our app from the share sheet. The file uploads and the transcript appears in your dashboard. No desktop sync, no AirDrop step.
06Custom vocabulary for medical or legal dictation?+
Yes. Paste drug names, case citations, or client names into the Custom vocabulary field on the job form. We pass them to the recognizer as hints, which helps with spelling but doesn't force matches on similar-sounding words.
07What happens to my memo after transcription?+
Source audio is permanently deleted within 24 hours. The transcript stays in your account until you delete it. We don't train on customer audio and we don't keep it for 'quality review.'
08Can I batch-process a backlog of old memos?+
Yes. Drag a folder of M4As into the upload area or zip them. Each file becomes a separate job with its own transcript. Useful if you have years of Voice Memos sitting unprocessed on your phone.

Drop your voice memo. See what comes out.

30 free minutes every month. No card. Works with iPhone M4A, Android AAC, and anything else your recorder app saves.

Start free