Features

  • Converts text to human-like speech with a compact 82M-parameter model
  • Runs locally without an internet connection
  • Offers multiple global accents
  • Mixes voices to create custom tones
  • Reads EPUB and PDF files and splits long content like e-books
  • Automates conversion via CLI and API, with live streaming support
  • Installs via pip or Docker

Pricing Details

The tool is based on an open-source, open-weight model and is completely free under the Apache-2.0 license for personal or commercial use, with no restrictions on the number of characters or minutes when running locally. There are no paid plans for the tool itself, but if used as a cloud service through third-party providers such as Together AI or DeepInfra, the cost in 2026 is approximately $0.60 per million characters, making it up to 95% cheaper than major competitors.