Summary

Pocket TTS is a lightweight text-to-speech application designed to run efficiently on CPUs. It generates audio from text with low latency and can handle infinitely long text inputs. The application supports Python 3.10 and above and requires PyTorch 2.5+, but does not need the GPU version of PyTorch.

Key Features

Low latency audio generation
Infinitely long text input handling
Small model size
CPU-based processing
Voice cloning support
Pre-made voice catalog
Python API and CLI
Local server support

About Pocket TTS


The application has a small model size of 100M parameters and uses only 2 CPU cores. It can stream audio and has a faster than real-time speed of approximately 6x real-time on a MacBook Air M4. Pocket TTS also supports voice cloning and has a catalog of pre-made voices, including alba, marius, and javert, among others.


Pocket TTS can be used as a Python library, and its functionality can be accessed through a command-line interface or a local server. The application has a web interface that can be accessed at http://localhost:8000, allowing users to input text and select different voices. It also has a serve command that keeps the model in memory between requests, making it faster than the command line.

Get more likes & reach the top of search results by adding this button on your site!

Embed button preview - Light theme
Embed button preview - Dark theme
TurboType Banner

Subscribe to the AI Search Newsletter

Get top updates in AI to your inbox every weekend. It's free!