Text-to-Speech & Voice Synthesis

10 repos

Pre-trained multilingual and multilingual text-to-speech models built on modern transformer architectures, designed for inference and deployment. The cluster includes implementations across multiple languages (English, Spanish, and others) with model variants optimized for different scales, alongside supporting infrastructure for serving these models via standard endpoints. Most repositories focus on making TTS models accessible and production-ready rather than implementing novel synthesis algorithms.

Related clusters