---
title: "YouTube to text with speakers and timestamps"
description: "Convert a public YouTube video into a timestamped transcript you can search, cite, and export. Start with 60 transcribed minutes per week."
canonical: "https://verbafy.io/youtube-to-text"
last-updated: "2026-09-18"
---

# YouTube to text

Turn a public YouTube video into usable text. Paste a public YouTube URL. Verbafy returns a Transcript with speaker labels, clickable timestamps, and source playback.

[Start with 60 transcribed minutes per week.](/app)

## Convert a YouTube video to text

1. Open [the app](/app).
2. Paste a public YouTube URL.
3. Wait for the Transcript.
4. Read the text, jump to a timestamp, then export TXT, Markdown, JSON, SRT, VTT, or ZIP.

Verbafy does not transcribe playlists, channel batches, or private YouTube videos.

## Free YouTube transcription limits

The Free Plan includes 60 transcribed minutes each UTC week. No signup is required to start. Guest sessions expire after seven days. Signing in claims the guest Transcripts.

See [pricing](/pricing) for Starter and Pro allotments.

## YouTube captions versus best-in-class verifiable ASR

YouTube captions are useful when they exist. They can be missing, delayed, or poorly punctuated. Verbafy transcribes the audio with best-in-class verifiable ASR and returns a speaker-labeled Transcript. You can still preview the original captions. That is the difference between pulling existing captions and creating a speaker-labeled Transcript.

## Dialect detection and mixed-language speech

Dialect detection is built in. You do not pick a dialect code. Regional speech such as Quebecois French, Mexican Spanish, or Brazilian Portuguese stays in the transcript. When speakers switch languages mid-sentence, each language is kept. Coverage includes 99+ languages.

## Speaker labels and AI-inferred names

Verbafy separates speakers. It infers names when they are identifiable. Names can stay generic or empty. Crosstalk and similar voices can cause errors.

## Clickable timestamps and source playback

Each segment links back to the YouTube player at that time. This is not word-level media editing.

## Summary and cited Chat

After the Transcript is ready, Verbafy can add an overview and key points. Summary generation can soft-fail. Cited Chat is available after a separate indexing step. Full Library Search is **SOON**.

## Download TXT, Markdown, JSON, SRT, VTT, or ZIP

Every plan can export those formats. There is no direct CMS, NLE, or social-publishing integration.

## Accuracy

Transcripts land at about 96.8% Benchmark Word Accuracy on an independent STT test (3.2% WER). That is evidence, not a guarantee for every file. Details: [How to evaluate transcription accuracy claims](/blog/how-to-evaluate-transcription-accuracy-claims).

## Frequently asked questions

## Can I transcribe any YouTube video?

You can transcribe public YouTube videos. Private, unlisted-without-access, playlist, and channel-batch jobs are not supported.

## Is YouTube to text free?

Yes, within the Free Plan: 60 transcribed minutes per week.

## Where do I start?

[Start with 60 transcribed minutes per week.](/app)

See also: [How to transcribe a YouTube video](/blog/how-to-transcribe-a-youtube-video), [How to transcribe a YouTube video without captions](/blog/how-to-transcribe-a-youtube-video-without-captions), and [How to evaluate transcription accuracy claims](/blog/how-to-evaluate-transcription-accuracy-claims).

Compare tools: [TurboScribe vs Verbafy](/compare/turboscribe) for file transcription, or [Descript vs Verbafy](/compare/descript) for video editing.

Agents: [Auth.md](/auth.md), [API docs](/docs), [create a transcript](/docs/api/transcripts/create-transcript).

```json
{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "Organization",
      "@id": "https://verbafy.io/#organization",
      "name": "Verbafy",
      "url": "https://verbafy.io",
      "inLanguage": "en",
      "knowsAbout": [
        "YouTube transcription",
        "Spotify episode transcription",
        "Meeting recording transcription",
        "Speaker diarization",
        "Transcript export"
      ],
      "hasOfferCatalog": {
        "@id": "https://verbafy.io/pricing#offers"
      },
      "contactPoint": {
        "@type": "ContactPoint",
        "contactType": "customer support",
        "email": "support@verbafy.io",
        "url": "https://verbafy.io/contact"
      }
    },
    {
      "@type": "WebPage",
      "@id": "https://verbafy.io/youtube-to-text#page",
      "url": "https://verbafy.io/youtube-to-text",
      "name": "YouTube to text with speakers and timestamps",
      "description": "Convert a public YouTube video into a timestamped transcript you can search, cite, and export. Start with 60 transcribed minutes per week.",
      "datePublished": "2026-08-19",
      "inLanguage": "en",
      "isPartOf": {
        "@id": "https://verbafy.io/#website"
      }
    },
    {
      "@type": "FAQPage",
      "@id": "https://verbafy.io/youtube-to-text#faq",
      "url": "https://verbafy.io/youtube-to-text",
      "inLanguage": "en",
      "mainEntity": [
        {
          "@type": "Question",
          "name": "Can I transcribe any YouTube video?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "You can transcribe public YouTube videos. Private, unlisted-without-access, playlist, and channel-batch jobs are not supported."
          }
        },
        {
          "@type": "Question",
          "name": "Is YouTube to text free?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "Yes, within the Free Plan: 60 transcribed minutes per week."
          }
        },
        {
          "@type": "Question",
          "name": "Where do I start?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "Start with 60 transcribed minutes per week. See also: How to transcribe a YouTube video, How to transcribe a YouTube video without captions, and How to evaluate transcription accuracy claims. Compare tools: TurboScribe vs Verbafy for file transcription, or Descript vs Verbafy for video editing. Agents: Auth.md, API docs, create a transcript."
          }
        }
      ]
    }
  ]
}
```