TranscriptYT
Get a free API key

Free YouTube tool

YouTube Audio to Text

Paste a YouTube link to turn what's said in the video into text with timestamps. If the video has captions you get them free in seconds; if it has none, AI listens to the audio and writes the transcript for you.

How to convert YouTube audio to text

  1. 1

    Copy the video link

    Any public video, Short, or finished livestream: music, talks, vlogs, or recordings in any language.

  2. 2

    Paste it above

    If the video has captions, the text appears in a few seconds. If it says the video has no captions, click Transcribe the audio with AI.

  3. 3

    Copy or download

    Copy the text with or without timestamps, or download TXT, SRT, VTT, PDF, or Markdown.

Captions first, AI when there are none

Most YouTube videos with speech already have captions, and reading those is instant and free. AI transcription is only for the rest: new uploads YouTube hasn't captioned yet, videos whose creator turned captions off, and music or recordings YouTube didn't caption.

Text you can search and reuse

The transcript comes with a timestamp on every line. Click a line to jump the video there, summarize it, translate it, or download it as a subtitle file. Developers can get the same audio-to-text transcripts through the API.

Need more?

Need transcripts at scale? Use the API

The same transcripts are available through the YouTube Transcript API: timestamped JSON, text, SRT, VTT, CSV, or Markdown, 150+ languages, and AI transcription for videos without captions. Or connect the YouTube MCP server to Claude, Cursor, or Codex and just paste links in chat.

curl "https://transcript-yt.com/v1/transcript?url=5f3Pn-N6yLc&format=text" \
  -H "Authorization: Bearer ts_live_..."
Get a free API key See the API

Common questions

Can I convert a YouTube video's audio to text without downloading it?

Yes. Paste the link and the transcript appears on this page. Nothing to download or install, and no audio file to upload.

Is it free?

Getting the captions a video already has is free. Transcribing the audio of a video with no captions uses AI and is on paid plans: the $3/month plan includes 1,000 credits, which covers about 16 hours of audio at 1 credit per minute.

How accurate is the AI transcription?

It uses OpenAI's Whisper large-v3 model, which handles clear speech in most major languages very well. Heavy background music, overlapping speakers, and strong accents lower the accuracy, so check names and numbers before you publish.

How long can the video be?

Videos up to about two hours are transcribed in one go; a two-hour video takes around two minutes. Captioned videos of any length load in seconds.

Which languages does it support?

Captions come in whatever languages the video has, and can be translated into 150+ languages. AI transcription detects the spoken language automatically and works in about 100 languages.