top of page

Speech-to-Speech Telegram AI Bot : ChatGPT + Eleven Labs | Python Bot

Dive into the world of dynamic user interaction with our Python script — a Telegram bot that seamlessly integrates various APIs to elevate the chatbot experience.

It is both:

  • Text to Speech (TTS) Bot

  • Speech to Speech (STS) Bot

Scripting Language : Python

Platforms used : Telegram, ChatGPT, OpenAI(Whisper), Eleven Labs

This Python script encompasses functionalities from Telegram, OpenAI (Whisper), Eleven Labs, and more, creating a sophisticated chatbot that responds to both text and voice messages. (Text to Speech (TTS) & Speech to Speech (STS) )

Key Functionalities:

Telegram API Integration:

Utilizes the telebot library to interact with the Telegram API.

Responds to '/start' and '/help' commands with a warm welcome message.

OpenAI API Integration (Whisper):

Processes text and voice messages from users.

Converts voice messages to text [Speech to Text (STT)] using the OpenAI Whisper API.

Utilizes ChatGPT from OpenAI to generate responses based on the entire conversation history.

Conversation Logging:

Logs user interactions by appending messages to user-specific log files.

Maintains a comprehensive history of the conversation, including both user and bot messages.

Text-to-Speech (TTS) with Eleven Labs API:

Converts generated text responses into voice messages using the Eleven Labs text-to-speech (TTS) API.

Sends voice messages back to users through the Telegram platform.

Error Handling:

Implements robust error handling to manage exceptions during the process.

Sends informative error messages back to users through the Telegram bot.

Continuous Polling:

Ensures seamless interaction by using bot.polling(none_stop=True) to continuously check for new messages from Telegram users.


Requires API tokens (Telegram, OpenAI, and Eleven Labs) and other parameters, set at the beginning of the script.

Additional Notes:

  • Some sections of the code are commented out, indicating potential areas for future implementation.

  • Debug information is printed during the process for easier troubleshooting.

What more can be done:

  • OCR functionality can be added to this using Google Cloud Vision

  • automations & Zapier Automations can be built upon this

Impactful User Experience:

This script effectively combines the capabilities of Telegram, OpenAI, and Eleven Labs APIs to create an interactive chatbot. Users can engage in a conversation using both text and voice messages, receiving text-based responses and even enjoying voice messages in return. The seamless integration of these APIs enhances the overall user experience, making the chatbot dynamic, responsive, and truly interactive.

3 views0 comments
bottom of page