This is my personal attempt to make the now near-dead Voicy bot work on todays tech, fixing issues here and there and making everything work nicely on Docker.

This repository contains the code for one of the most popular bots I've ever built for Telegram — @voicybot. It automatically converts all the audio messages to text when added to a group chat. Please, feel free to fork, add features and create pull requests so that everybody (over 12 000 000 people) can experience the features you've built.

You can also help by translating the bot to other languages or fixing some texts in existing languages by modifying the locales folder or at localize.borodutch.com.

• voicy — the main @voicybot code
• voicy-payments — payments service that used stripe to process payments for the Google Speech seconds of recognition; currently retired as the stats server for voicybot.com
• voicy-landing — borodutch.com landing page
• voicy-recognition — Recognition service for voicybot.com

1. Clone this repo: git clone https://github.com/bytebone/voicy
2. Edit the .env.sample file with your wit.ai tokens, telegram token and salt, and save it as .env
3. Run docker build --network=host -t bytebone:voicy
4. Run docker compose up

See examples in .env.sample file.

MIT — use for any purpose. Would be great if you could leave a note about the original developers. Thanks!