How to transcribe a video on iPhone

A lot of what people say to you now arrives as video: a recorded Zoom call, a lecture posted to the course site, a voice message with a face on it, a client walking through a problem on a screen recording. Watching it again is slow. Reading it is fast. This guide shows how to transcribe a video on iPhone with Memo, a free app for iOS 26 or later.

Memo takes the audio track from a video in your Photos library and gives you a transcript, a summary with a title, a to-do list and a chat that answers questions about it. The video itself is not changed.

Step 1: get the video into Photos

Memo imports videos from your Photos library, so the first step is to have the file there.

Screen recordings and videos you shot are already in Photos.
A video from Files, Mail or Messages: open it, tap Share, and choose Save Video. It appears in Photos.
A recorded call from a video-conferencing app: download the recording to the phone, then save it to Photos the same way.

Videos from the web are a copyright question before they are a transcription question. Transcribe your own calls, lectures you are allowed to record, and material you have the right to use.

Step 2: import the video into Memo

Open Memo and tap the plus button.
Choose Import video.
Pick the video from Photos.
Choose the engine. Memo tells you what happens to the audio before it happens.

Memo takes the audio track and processes it like a recording. The video stays in Photos.

Which engine for a video

On-device AI keeps the audio, the transcript and the summary on your iPhone. Nothing is uploaded. It needs an iPhone with Apple Intelligence (iPhone 15 Pro and later, every iPhone 16 and 17) and a language Apple supports on the device. For a recorded client call, this is the option that never puts the call on a server.
Cloud AI uploads the audio to Memo’s servers and works on every iPhone in more than 99 languages. The free tier accepts recordings up to 30 minutes and a daily allowance; Memo Pro lifts both.

The conditions are listed in Which iPhones and languages support On-device AI, and Does my audio leave my phone? explains exactly what each engine does with the audio.

Step 3: use the text

The transcript is timestamped. Tap a line and Memo plays that moment of the audio, so you can find the second where the client said the number.
The summary gives you the title, the key points and the decisions of a call without watching it.
The to-dos are the promises made in the video, with owners and dates when they were said.
The chat answers from the video’s words: “What were the two objections?” or “Draft a reply to the questions he asked.”

Everything Memo produces can be copied, shared, printed or exported as a PDF from the memo menu, or shared as a private link that opens in a browser. See Export a memo.

Three videos this works well for

A recorded meeting. Save the recording to Photos, import it, and you have the same summary and to-do list you would get from recording the meeting live. Our guide How to summarize a meeting recording on iPhone covers what to do with the result.

A lecture or a talk. Course videos, conference talks you were sent, a webinar you attended: the summary is the notes, the chat is the revision partner. How to turn a lecture into notes on iPhone has the study workflow.

A screen recording with narration. When someone walks you through a process on their screen, the transcript becomes the written procedure, step by step, in their words.

What to expect from the audio in a video

A video’s audio is usually worse than a recording made for the purpose: it was captured by a laptop microphone across a room, or compressed hard by a messaging app. Memo does its best with it, and the transcript is still far faster to read than the video is to watch. If the result says “No speech was detected”, the audio track was silent or too quiet; this article explains what to check.

The short version

Save the video to Photos, tap plus in Memo and choose Import video, pick On-device AI for privacy or Cloud AI for any phone and any language, and read the summary. The words come out; the video stays where it was.