UNITTS is a toolkit for running inference and benchmarking open-source text-to-speech (TTS) models. The announcement, published on June 9, 2026, states that it supports Chatterbox and Fish Audio s2-pro.
A unified interface may make it easier to compare engines and switch between them. The announcement provides no performance results, so run your own tests before choosing an option.
For a comparison, use the same text, settings, and criteria for each engine. Record latency, perceived quality, and failures, and check whether the licenses and runtime requirements fit your use case.
If you use AI to study or apply the material, avoid sending personal data or internal information without authorization. Review the chosen tool’s retention and access rules, and use test data where possible.