KoljaB/RealtimeTTS
Python text-to-speech library for real-time synthesis with support for neural voice models.
Not currently ranked — collecting fresh signals.
star history
RealtimeTTS converts text to audio with low latency, accepting strings, generators, and LLM token streams as input. It supports multiple TTS engines including local system voices, cloud APIs, free service wrappers, local neural models, and voice-cloning stacks. The library can play speech locally, stream audio chunks to other processes, or write WAV files.
Frequently asked
- What is KoljaB/RealtimeTTS?
- Python text-to-speech library for real-time synthesis with support for neural voice models.
- Is RealtimeTTS open source?
- Yes — KoljaB/RealtimeTTS is open source, released under the MIT license.
- What language is RealtimeTTS written in?
- KoljaB/RealtimeTTS is primarily written in Python.
- How popular is RealtimeTTS?
- KoljaB/RealtimeTTS has 4k stars on GitHub.
- Where can I find RealtimeTTS?
- KoljaB/RealtimeTTS is on GitHub at https://github.com/KoljaB/RealtimeTTS.