Beta

Read any YouTube video — timestamped, on your Mac

Paste a link. Player on the left, timestamped transcript on the right, kept in sync. Captions load instantly; nothing is uploaded.

Download for Mac
The YouTube Explorer — video and transcript, in sync

Paste, read, click to seek

  1. Instant captions

    Drop a URL and read a scrollable, timestamped transcript in seconds — before any audio is processed.

  2. Click any line

    The player jumps to that moment; a floating play button follows your scroll so you always start “from here”.

  3. Speaker labels on demand

    One button runs the on-device pipeline — Parakeet-TDT plus diarization — for a speaker-labelled transcript.

Not just another transcript site

Most online tools post a URL to a server and hand back plain text. Vocateca is a native macOS app built for working with a lot of audio.

Vocateca vs typical online YouTube transcript tools
VocatecaTypical online tools
Where it runsOn your Mac — URL and audio never leave itServer-side — your link and audio hit their servers
TimestampsCore: every segment timed, click to seekOften optional or plain-text only
Speaker labelsYes — on-device diarization, carried into CSVRare
No captions?Falls back to real on-device transcriptionUsually fails — captions only
Export formatsmd, txt, srt, vtt, csv, json, okfPlain text, sometimes SRT
Beyond one videoPlaylists, channel subscribe, auto-downloadOne video at a time
AutomationBuilt-in CLI + MCP transcript commandWeb UI or a paid API
AccountNone — no sign-up, no creditsOften sign-up or metered credits

What we leave out, on purpose: No browser extension, no cloud chat, no server API, no AI summaries — off-model for a native, private app. Vocateca does one job well: clean, structured text out of the audio you follow.

More than a single video

Every format, speakers included

Subtitles as VTT/SRT, structured segments as CSV/JSON, LLM-ready Markdown. CSV carries a speaker column when diarized on-device.

All export formats

Playlists, channels, daemon

Paste a playlist or a CSV of links to transcribe in bulk — or subscribe to a channel and let a daily daemon do it.

On-device, no account

Captions from YouTube, transcription local on Apple Silicon, transcript stays on your Mac unless you export it.

How privacy works
CLI & MCP

Scriptable, and usable by AI agents

The same extraction is a command-line tool and — automatically — an MCP tool your AI assistant can call.

Vocateca's MCP server is derived from its CLI, so transcript shows up as a tool in Claude with no extra setup.

See LLM workflows

Extract a timestamped transcript

$ vocateca transcript "https://youtube.com/watch?v=…" --format vtt
WEBVTT

00:00:00.000 --> 00:00:04.120
Hello and welcome
…

Read YouTube instead of watching it

Download Vocateca for Mac