transcript extractor

Yet another Telegram Voice Recognition bot but using vosk and supports 20+ languages.

Deploy to Heroku


Local Deploying

  1. Make sure you have FFmpeg.

  2. Clone the repo

    git clone
  3. Enter the directory

    cd Transcript-Extractor-Bot
  4. Install all requirements using pip.

    pip3 install -r requirements.txt
  5. Run the file


Environment Variables

  • API_ID – Get this from
  • API_HASH – Get this from
  • BOT_TOKEN – Get this from @BotFather.
  • SEND_AS – transcript sending format (TXT or PDF).
  • LANGUAGE_CODE – vosk supported language(code), see supported languages here.
  • MODEL_DOWNLOAD_URL – language model download link (see available models here.



View Github