RecordtoNotes

YOUTUBE TRANSCRIPT

Get a YouTube transcript.

Original captions, or a transcript made on your device. Search, edit, export or save to Notion.

Free captions · No signup

Start with a video

Public videos up to 60 minutes. Captions are free without an account. Videos without captions are transcribed on this device after signing in, 5 per day.

Captions free, no signupPublic videos up to 60 minutesNo captions? Transcribed on your device
  1. 01
    Paste a link

    Any public video up to 60 minutes.

  2. 02
    Get the text

    Original captions, or sign in and let your device transcribe, 5 videos per day.

  3. 03
    Make the words yours

    Edit, copy, download or save to Notion.

For videos without captions, our service on Cloudflare fetches the audio once and deletes it after the transfer. Video retrieval has limited shared daily capacity; local audio files are not affected.

Saved transcripts and Notion settings live in My library.

How to get a YouTube transcript

  1. Copy the link of a public YouTube video up to 60 minutes long and paste it above.
  2. Choose Get transcript. When the video has captions, the text opens in the workspace with timestamps that link back to the video.
  3. Search, edit and copy the text, export it, or save it to Notion.

Captions or a transcript made on your device

Most videos have captions: subtitles added by the uploader, or YouTube’s automatic captions in the spoken language. Record to Notes uses these original tracks, never machine translations. Getting captions is free and needs no account.

When a video has no captions, sign in to transcribe it on your device instead, up to five videos a day. Our service on Cloudflare fetches the audio once and deletes it after the transfer; speech recognition then runs in your browser with the same Whisper models used for audio files. The first run downloads a speech model, and speed depends on your device.

Export as plain text, Markdown or subtitles

Limits

What it does not do

Record to Notes does not download videos or audio files, summarize videos or process playlists. It gives you the full text of one video at a time, up to ten in the workspace.

Questions

Is it free?

Yes. Captions and on-device transcription are free. Saving to Notion is also free and needs an account.

Can I get a YouTube transcript without timestamps?

Yes. Choose Copy or export TXT for plain paragraphs. Markdown and SRT keep the timestamps.

Which languages are supported?

Captions come in the language spoken in the video. On-device transcription covers 30 languages; any language other than English uses the Best model, a download of about 590 MB.

Where does my data go?

The video link goes to our retrieval service, which contacts YouTube for you without your account or cookies. Details are in the privacy policy.

Transcribe an audio file · Help

Help

How do I import a recording?

Choose up to 10 audio or video files saved on your device, or drop it into the tool. Check its name and duration, select the spoken language, then press Start transcription.

On iPhone, use Share in Voice Memos to save the recording to Files or transfer it to your computer. On Android, use Share or Export in your recorder app. Choose the actual audio file, not a cloud sharing link or a recorder project.

If a recording is only a cloud placeholder, download it first. A laptop or desktop is recommended for longer recordings and larger models.

Which files can I use?

Audio: MP3, M4A (AAC), WAV, FLAC, OGG, Opus, AAC and M4B. Video: MP4, MOV, WebM, MKV and TS; only the audio track is used. Local files have no product size or duration cap. Files are read and decoded in sections. Codec support, memory and speed depend on your browser and device.

Not supported: Apple Lossless (ALAC) M4A, AIFF, WMA, AMR voice recordings (.amr or .3gp), AVI, ADPCM WAV, and videos with Dolby (AC-3 or E-AC-3) audio. Convert these to MP3 or WAV first; renaming a file does not convert its audio. An unsupported file is reported as soon as you add it.

YouTube links and Notion

Paste a public YouTube link on the homepage or the YouTube transcript page. Original captions are free without an account. A video without captions can be transcribed on your device after signing in, up to five per day; the audio is fetched once by a service hosted on Cloudflare and is not kept. Saving to Notion requires signing in and authorizing your workspace. Cloud transcription is not open yet.

TXT, SRT, Markdown and ZIP downloads include the full available text, even for long recordings. Cancelled or failed recordings can export their partial text. Use Save to Notion beside Export to prepare a local text draft and continue in a new tab. Your recording stays open; login and Notion connection happen in My library. Notion saves currently accept up to 60 minutes, 10,000 segments and 1 MB of text per recording.

MP3

A supported MP3 can be selected directly, including recordings longer than 60 minutes. Keep this page open while processing.

M4A

Most M4A files contain AAC audio and work. iPhone Voice Memos recorded with Audio Quality set to Lossless use Apple Lossless, which Chrome and Edge cannot decode: choose Compressed for new recordings, or convert existing ones to AAC M4A or WAV.

WAV and damaged files

WAV works with 8-, 16-, 24- and 32-bit PCM, 32-bit float, µ-law and A-law audio, decoded in sections. If a file fails, check that it plays in your recorder, export it again, or try a shorter recording on a computer.

Why does a model download? Where does my audio go?

Speech recognition runs on your device. Selected files and your transcript stay in the current page; the original file is unchanged. The browser downloads model and runtime files, and the site sends anonymous usage events without audio, filenames or transcript text.

Fast and Balanced are intended for English. Selecting another language switches to Best. Open Quality before starting to review quality and approximate model download sizes. Larger models need more memory; preparation takes time even after downloading.

Speaker labels are also found on your device. If you know how many people speak, set Speakers in Settings; choose One speaker to skip this step. After transcription you can rename speakers, or give two the same name to merge them.

The browser may reuse cached models, but caches can be cleared or evicted. Keep the tab open while it works. For download errors, check your connection and retry. For memory problems, try a shorter file on a computer.

The full transcript is free, with no signup or commercial minutes quota. Format and device limits still apply. Refreshing clears the local audio queue. Saving to Notion is optional and requires signing in; its existing transfer limits are separate from local transcription.

How do I check, edit and save the text?

Search for a phrase and choose Next to move through matching segments. Long transcripts are shown in pages of up to 100 segments. Search covers the entire transcript and opens the matching page. Click a timestamp to listen back. Choose Edit to correct the text, then Done editing. Timestamps cannot be edited.

For lectures, check names and technical terms against the recording. For podcasts, verify wording and timing before using a subtitle export. Speaker labels are not automatically identified. Chapters and extracted key points are optional navigation aids and update when you edit the text.

Copy takes the complete edited text. Export offers TXT for plain text, SRT for subtitles and Markdown for text with timestamps and chapters.

You can cancel during file checks, model preparation or recognition. Completed sections remain a partial transcript that you can edit and export. Retrying starts from the beginning; export anything you want to keep before replacing a result.

Copy or export before refreshing, leaving or closing the page. Files, text and edits only live in page memory and are not saved automatically.

Close or press Escape to return.