How to Transcribe a Video on iPhone (Get Text from Any Clip)

You recorded a lecture, an interview, or a talking-head clip on your iPhone, and now you need the words as text you can copy, search, quote, or turn into captions. iOS has a few built-in tools that get you part of the way, but none of them turns a saved video into a clean, timestamped transcript on its own.

This guide covers what the built-in options actually do, the "extract the audio first" route, and the fastest way to transcribe a video on iPhone into editable text or an SRT caption file.

Quick answer

• Want a full transcript of a saved video? Upload it (or paste its link if it's already on YouTube, TikTok, Instagram, or X) to a transcription tool like SkyScribe and export text or SRT.
• Only need to read along live? iPhone's Live Captions accessibility feature shows on-screen captions while audio plays, on supported devices and languages, but it doesn't save a transcript file.
• Already have the audio as a recording? Recent iOS versions can show transcripts for Voice Memos and Notes audio recordings on supported devices and languages.

What iPhone can do on its own

Live Captions (read along, no file)

On supported iPhones and languages, Settings → Accessibility → Live Captions displays real-time captions for audio playing on the device, including video in the Photos app. It's great for following a clip in a noisy room. It doesn't give you a saved, editable transcript, though, so you can't export or search it later.

Voice Memos and Notes transcripts (audio only)

Recent iOS versions can transcribe audio recordings in Voice Memos and in Notes on supported devices and languages. That helps when you captured audio directly, but it doesn't transcribe a video sitting in your camera roll. You'd need to get the audio out of the video first, and even then the transcript is designed for reading, not for caption timing. We cover this in more depth in does Voice Memos transcribe?.

Live Text (on-screen text, not speech)

Live Text can copy text that is visible in a paused video frame, like a slide or a sign. It doesn't transcribe what people are saying.

Bottom line: iOS has good pieces, but no built-in "video in, transcript file out" button.

Method 1: Upload the video and transcribe it (fastest)

This is the most direct route for clips saved in Photos or Files.

1. Open SkyScribe in Safari on your iPhone.
2. Choose upload and pick the video from Photos or Files.
3. Wait for the transcript, then review it. Fix names, brand terms, and anything the audio made hard to hear.
4. Export what you need:

• Text for notes, quotes, or a blog draft
• SRT for captions in CapCut, DaVinci Resolve, Premiere, or YouTube
• A translated transcript if your audience speaks another language

Tip: If the video is long and you're on cellular, upload over Wi-Fi. A video file is much larger than its audio track.

Method 2: Extract the audio first, then transcribe

If the video file is large, or you only care about the speech, pulling the audio out first makes uploads faster and lets you reuse the audio elsewhere (as a podcast clip, voice note, or MP3).

1. Extract the audio from the video. Our step-by-step guide shows how to extract audio from video on iPhone without extra apps, and extract audio from iPhone video covers more options.
2. Upload the audio file (M4A, MP3, and similar) to SkyScribe.
3. Review and export as text or SRT.

Audio-only files upload faster and give you the same transcript, because the speech is what gets transcribed either way. If you need MP3 specifically, see MP3 to text online.

Method 3: The video is already online, so paste the link

If the clip is already posted, you don't need the file at all. Copy the share link and paste it into SkyScribe:

• YouTube (including Shorts): see paste a YouTube URL, get a transcript
• TikTok: see how to transcribe a TikTok video to text
• Instagram Reels: see Instagram Reel transcript
• X (Twitter): see X video transcript

This is especially useful when you're researching someone else's video and only have the URL.

Getting a better transcript from iPhone recordings

Transcription accuracy depends mostly on the audio. A few habits make a big difference:

• Get the mic close to the speaker. iPhone mics are good, but distance and room echo hurt accuracy more than anything else.
• Avoid background music under speech when you can. Music competes with voices.
• Record interviews with a clip-on or wireless mic if you do them often.
• Keep one speaker at a time. Crosstalk is hard for any transcriber, human or AI.
• Review names and jargon once. Fix them in the transcript before exporting captions or translating, so mistakes don't carry into every format.

Turning the transcript into captions

Once you have an SRT, you can add captions almost anywhere:

• Editing on desktop: import SRT into DaVinci Resolve, or see add an SRT to video on Windows or Mac.
• Need another language? Translate an SRT without breaking timestamps.
• Short-form social: burned-in captions are usually the most reliable on TikTok and Reels, where many viewers watch muted.

FAQ

Can iPhone transcribe a video for free without an app? iPhone can show live captions while a video plays (on supported devices and languages), and it can transcribe some audio recordings, but it doesn't create a saved transcript file from a video in your camera roll. A browser-based tool like SkyScribe handles that without installing anything.

Do I need to convert the video to audio first? No. You can upload the video directly. Extracting audio first just makes the upload smaller and faster.

Can I get timestamps or subtitles, not just text? Yes. Export as SRT to get timestamped captions you can import into video editors or upload to YouTube.

Does this work for screen recordings? Yes, as long as the screen recording captured audio. If it's silent, there's nothing to transcribe. Check that microphone audio or system audio was on when you recorded.

Can I translate the transcript? Yes. SkyScribe can translate the transcript, and you can export the translation as text or SRT.