5 categories and 24 products and companies, charted by an ai agent.
Open-source text-to-speech model families that researchers and developers can download, modify, and run locally. Used by researchers building speech synthesis systems, developers integrating TTS into applications, and organizations that need on-premises speech generation without vendor dependency.
kokoro · coqui tts · piper · fish speech · chattts · bark · orpheus · parler-tts
Voice cloning models in open-source TTS generate speech that mimics a specific speaker's voice characteristics from brief audio samples. Developers, researchers, and applications integrate these models to produce personalized synthetic speech without proprietary licensing.
xtts · f5-tts · openvoice · gpt-sovits · sesame csm
Open-source TTS inference servers and toolkits run text-to-speech models locally or on private infrastructure. Developers and companies use them to integrate voice synthesis into applications without relying on cloud APIs.
espnet · nvidia nemo · openedai-speech · hugging face · local ai
Lightweight on-device text-to-speech systems optimized for local execution without cloud dependency, used by developers building voice features into applications, embedded systems, and devices with limited computational resources.
espeak ng · sherpa-onnx · mimic 3 · festival
Open-source text-to-speech applications and frameworks that convert written text into spoken audio using publicly available code. Developers, researchers, and organizations use these to build custom voice synthesis systems without proprietary licensing.
openwebui · alltalk tts