All open source
Open SourceVoice & Media42k

Coqui TTS

Deep-learning toolkit for text-to-speech with 1100+ languages.

Coqui TTS (the TTS library) is an open-source deep-learning toolkit for text-to-speech, providing pretrained models and training recipes for a wide range of speech synthesis architectures. It supports multi-speaker and multilingual synthesis and voice cloning, and includes the XTTS model; the original company has shut down but the repository remains a widely used reference.

Repository

coqui-ai/TTS

Language

Python

What you'd build with it

  • Generate synthetic speech from text using pretrained multilingual voices
  • Clone or adapt a voice from a short reference sample for narration or agents
  • Train or fine-tune custom TTS models on your own speech data

Tags

ttsvoice-cloningmultilingual