---
title: "FAQ: YouTube, Spotify, meetings, and free plans"
description: "Answers about YouTube to text, Spotify episodes, meeting recordings, accuracy, and the Free Plan."
canonical: "https://verbafy.io/faq"
last-updated: "2026-09-15"
---

# Frequently asked

## How do I transcribe a YouTube video to text?

Paste a public YouTube URL in [the app](/app). Verbafy returns a Transcript with speaker labels, clickable timestamps, and source playback. Playlists, channel batches, and private YouTube videos are not supported. See [YouTube to text](/youtube-to-text).

## Can I transcribe a YouTube video for free?

Yes. The Free Plan includes 60 transcribed minutes each week. No credit card. See [pricing](/pricing).

## Does Verbafy use existing YouTube captions?

When captions exist, you can preview them. That is YouTube captions versus best-in-class verifiable ASR: Verbafy still transcribes the audio into a speaker-labeled Transcript. That is different from downloading existing captions.

## Does Verbafy detect regional dialects?

Yes. Dialect detection is built in. You do not pick a dialect code. The transcript follows regional speech such as Quebecois French, Mexican or Argentine Spanish, Brazilian Portuguese, and US, UK, or Australian English.

## Can Verbafy transcribe mixed-language speech?

Yes. When speakers switch languages mid-sentence, Verbafy keeps each language in the transcript. It does not force the whole file into one language. Coverage includes 99+ languages, with fallback when the primary model does not cover the detected language.

## Can I get a transcript from a Spotify podcast episode?

Yes, from a canonical Spotify episode link (`open.spotify.com/episode/…`). Show pages, playlists, Apple Podcasts, and RSS URLs are not supported. See [Spotify to text](/spotify-to-text).

## Can I transcribe a Teams, Zoom, or Google Meet recording?

Yes. Export the recording, then upload the file. Verbafy does not join, record, or live-transcribe those calls. See [meeting to text](/meeting-to-text).

## Does Verbafy join live Zoom or Teams calls?

No. Meeting Recording Transcription starts from a file you already have. A live meeting bot should win if you need attendance or a live transcript.

## How do I transcribe audio or an MP3 to text?

Upload a private audio or video file in [the app](/app). Private uploads support MP3, AAC, M4A, WAV, AIFF, FLAC, OGG, Opus, MP4, MOV, and MKV. Files can be up to 10 GB. These private audio or video uploads include meeting recordings and interviews.

## How accurate is the transcription?

Transcripts land as export-ready files at about 96.8% accuracy on an independent STT benchmark (3.2% WER). That figure is Benchmark Word Accuracy (`100% − WER`) for the AssemblyAI model Verbafy currently uses. Coval lists that AssemblyAI result as best-in-class 3.2% WER on the [30-day Speech-to-Text Benchmarks](https://benchmarks.coval.ai/stt?window=30d). The Coval WER snapshot varies. Last checked on 8 September 2026. Real-world results vary by audio quality; the figure is evidence of quality, not a guarantee on every video. A lower independently measured number is more useful than a 99%+ marketing claim with no named method. See [How to evaluate transcription accuracy claims](/blog/how-to-evaluate-transcription-accuracy-claims).

## Can I download a transcript as TXT, SRT, or VTT?

Yes. Every plan can download TXT, Markdown, JSON, SRT, VTT, and a ZIP bundle. AI-inferred speaker names when identifiable, clickable timestamps, and optional Auto translate are included.

## What is the difference between Starter and Pro?

Starter includes 1,000 transcribed minutes / month. Pro includes 3,000 transcribed minutes / month and 33% lower cost per transcribed minute than Starter. Both paid plans include 99+ languages and unlimited AI chat. Monthly Starter and Pro include a 3-day Paid-plan Trial with a card on file. [See pricing](/pricing) for current prices.

```json
{
  "@context": "https://schema.org",
  "@type": "FAQPage",
  "@id": "https://verbafy.io/faq#faq",
  "url": "https://verbafy.io/faq",
  "inLanguage": "en",
  "mainEntity": [
    {
      "@type": "Question",
      "name": "How do I transcribe a YouTube video to text?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Paste a public YouTube URL in the app. Verbafy returns a Transcript with speaker labels, clickable timestamps, and source playback. Playlists, channel batches, and private YouTube videos are not supported. See YouTube to text."
      }
    },
    {
      "@type": "Question",
      "name": "Can I transcribe a YouTube video for free?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Yes. The Free Plan includes 60 transcribed minutes each week. No credit card. See pricing."
      }
    },
    {
      "@type": "Question",
      "name": "Does Verbafy use existing YouTube captions?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "When captions exist, you can preview them. That is YouTube captions versus best-in-class verifiable ASR: Verbafy still transcribes the audio into a speaker-labeled Transcript. That is different from downloading existing captions."
      }
    },
    {
      "@type": "Question",
      "name": "Does Verbafy detect regional dialects?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Yes. Dialect detection is built in. You do not pick a dialect code. The transcript follows regional speech such as Quebecois French, Mexican or Argentine Spanish, Brazilian Portuguese, and US, UK, or Australian English."
      }
    },
    {
      "@type": "Question",
      "name": "Can Verbafy transcribe mixed-language speech?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Yes. When speakers switch languages mid-sentence, Verbafy keeps each language in the transcript. It does not force the whole file into one language. Coverage includes 99+ languages, with fallback when the primary model does not cover the detected language."
      }
    },
    {
      "@type": "Question",
      "name": "Can I get a transcript from a Spotify podcast episode?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Yes, from a canonical Spotify episode link (open.spotify.com/episode/…). Show pages, playlists, Apple Podcasts, and RSS URLs are not supported. See Spotify to text."
      }
    },
    {
      "@type": "Question",
      "name": "Can I transcribe a Teams, Zoom, or Google Meet recording?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Yes. Export the recording, then upload the file. Verbafy does not join, record, or live-transcribe those calls. See meeting to text."
      }
    },
    {
      "@type": "Question",
      "name": "Does Verbafy join live Zoom or Teams calls?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "No. Meeting Recording Transcription starts from a file you already have. A live meeting bot should win if you need attendance or a live transcript."
      }
    },
    {
      "@type": "Question",
      "name": "How do I transcribe audio or an MP3 to text?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Upload a private audio or video file in the app. Private uploads support MP3, AAC, M4A, WAV, AIFF, FLAC, OGG, Opus, MP4, MOV, and MKV. Files can be up to 10 GB. These private audio or video uploads include meeting recordings and interviews."
      }
    },
    {
      "@type": "Question",
      "name": "How accurate is the transcription?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Transcripts land as export-ready files at about 96.8% accuracy on an independent STT benchmark (3.2% WER). That figure is Benchmark Word Accuracy (100% − WER) for the AssemblyAI model Verbafy currently uses. Coval lists that AssemblyAI result as best-in-class 3.2% WER on the 30-day Speech-to-Text Benchmarks. The Coval WER snapshot varies. Last checked on 8 September 2026. Real-world results vary by audio quality; the figure is evidence of quality, not a guarantee on every video. A lower independently measured number is more useful than a 99%+ marketing claim with no named method. See How to evaluate transcription accuracy claims."
      }
    },
    {
      "@type": "Question",
      "name": "Can I download a transcript as TXT, SRT, or VTT?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Yes. Every plan can download TXT, Markdown, JSON, SRT, VTT, and a ZIP bundle. AI-inferred speaker names when identifiable, clickable timestamps, and optional Auto translate are included."
      }
    },
    {
      "@type": "Question",
      "name": "What is the difference between Starter and Pro?",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "Starter includes 1,000 transcribed minutes / month. Pro includes 3,000 transcribed minutes / month and 33% lower cost per transcribed minute than Starter. Both paid plans include 99+ languages and unlimited AI chat. Monthly Starter and Pro include a 3-day Paid-plan Trial with a card on file. See pricing for current prices."
      }
    }
  ]
}
```