About OpenSpeech

ElevenLabs is expensive. Open-source TTS has caught up — but the models are scattered across GitHub, Hugging Face, and a dozen comparison blog posts. Finding one and actually hearing it usually means cloning a repo, fighting CUDA, and praying the weights still download.

OpenSpeech is an experiment to fix that:

  • Every voice reads the same three scripts.
  • Specs, license, and install in one place.
  • Filter by license, VRAM, language, capability.
  • Add a model with one PR.

Models curated from awesome-ai-voice. Samples generated via Replicate. Not affiliated with any model author.

The three scripts

Neutral — baseline naturalness with no tricky words.

Emotional — tests prosody and expressiveness.

Numbers & Dates — the common failure mode for every TTS model.

Contribute GitHub