YouTube → text in Telegram

When it is easier to read than to watch: send a video link and get text ready for reading.

AI assistants & Telegram bots · Documents

About the project

A Telegram bot turns the transcript of a YouTube video into coherent, neatly formatted text. The solution is handy for training videos, technical breakdowns and other content that is easier to take in by reading.

You send the bot a link, and it gets the transcript and passes it to an AI editor. The model removes filler words, repetitions and recognition artifacts, fixes obvious errors and splits the text into logical paragraphs.

The result arrives right in Telegram. The bot automatically splits a long text into several messages and sends them in order — without manual copying and processing of the transcript.

How it works

  1. YouTube video link
  2. Getting the transcript
  3. AI editing
  4. Readable text in Telegram

Features

  • Getting the transcript from a video link.

  • Cleaning and literary polishing of the text with AI.

  • Splitting into paragraphs for easy reading.

  • Automatic sending of long texts in parts.

  • Restricting access to the bot to allowed Telegram chats.

Where it can be used

  • Self-education: reading lectures, lessons and technical breakdowns instead of watching.
  • Corporate training: working with training materials published on YouTube.
  • Analytics and editorial work: turning video sources into text for further study.

Technologies

  • n8n
  • Telegram
  • OpenAI
  • YouTube-Transcript.io

More projects

All projects

AI assistants & Telegram bots

Calendar AI & Chronos

Plan your tasks and log working time — with an ordinary message in Telegram.

A personal AI assistant: Google Calendar events and time tracking in Google Sheets from a text or voice message.

Result Create or view a calendar event in 10–15 seconds

  • Telegram
  • n8n
  • LLM
  • Speech recognition
  • Google Calendar
  • +1

Voice & meetings · Documents

Local transcription of large audio files

Hours of recordings turned into ready text — without cloud service limits.

Batch transcription of audio recordings on your own computer with GPU acceleration, fully offline.

Result About 60 hours of lectures processed in about 5 hours on a GPU

  • Python
  • Faster Whisper
  • NVIDIA CUDA
  • FFmpeg
  • n8n
  • +2

AI assistants & Telegram bots · Voice & meetings

AI dictation in Telegram

Dictate a message — get neat text, ready to send.

Voice messages become edited text right in Telegram.

  • n8n
  • Telegram
  • Whisper
  • GPT-4.1

Start with one process.

Describe what is currently done manually, what data is involved and what result you would like to achieve. You do not need a technical specification or a chosen model to begin.

Please do not share trade secrets, source code, or sensitive personal data before an NDA (non-disclosure agreement) is signed.