Convert text to speech with customizable parameters using a simple metalanguage
Telegram TTS Bot
A Telegram bot that converts text to audio using a local Chatterbox TTS server
Users can specify TTS parameters using a simple metalanguage directly in their messages
The metalanguage uses a simple key-value pair format where the main text comes first,
followed by parameters using the **PARAM:value format.
**PARAM:value format
This example sets CFG to 0.8, EXAG to 1.2, and TMP to 1.1
| Parameter | Description | Default | Range |
|---|---|---|---|
| CFG | Classifier-free guidance scale | 0.5 | 0.0 - 2.0 |
| EXAG | Expression exaggeration | 0.4 | 0.0 - 2.0 |
| TMP | Temperature for generation randomness | 0.8 | 0.0 - 1.5 |
| SPD | Speed factor for speech tempo | 1.0 | 0.25 - 4.0 |
| LANG | Language for text-to-speech generation | en | en, es, fr, de, it, pt, ru, ja, ko, zh |
These preset configurations are optimized for different use cases and can be used as starting points for your TTS generation.
Perfect for educational content and documentaries
Dramatic and theatrical performances
Clear and precise technical content
Energetic marketing and promotional content
Contemplative and philosophical content
Basic conversational testing
User types text with optional TTS parameters
Bot extracts main text and parameter values
Parameters are forwarded to local TTS server
TTS server processes text with custom parameters
Generated audio file is sent back to the user
Our pricing is straightforward and transparent: $1.00 per 2 minutes of generated speech. This rate applies regardless of the language, parameters, or complexity of your text.
All purchases are made through Telegram Stars, Telegram's built-in payment system. This provides a secure and convenient way to pay directly within the Telegram app.
Note: The exchange rate may vary. Current rate is approximately 100 stars for $2.00 USD.
To help you estimate costs, here's a reference guide based on average speech patterns:
Note: Character counts vary based on language, speaking pace, and text complexity. The 1,700 character estimate is based on average French speech patterns at 135 words per minute.
Send your text message to the Telegram bot with optional TTS parameters
The system generates audio based on your text length and specified settings
You're charged via Telegram Stars ($1.00 = 50 Stars) for every 2 minutes (or portion thereof) of generated speech
If you generate a 4-minute speech:
Automation platform handling message processing and TTS server communication
Handles user interactions and message delivery in Telegram
Chatterbox TTS server for high-quality text-to-speech generation
Send a message to the Telegram bot with your desired text
Use the metalanguage syntax to customize voice settings
The bot will generate and send back the audio file with your specified settings