Decentralized yet unified efforts to accelerate research for open text-to-speech systems.
A continually updated arena to find the best open TTS model currently available. Vote on the latest models and help advance TTS research.
Visit Arena →A large-scale podcast dataset containing tens of thousands of hours of audio with pre-computed diarization for speech research.
mrfakename
Vaibhav (VB) Srivastav (OpenAI)
Clémentine Fourrier (Hugging Face)
Lucain Pouget (Hugging Face)
Yoach Lacombe (Hugging Face)
Main Horse (Hugging Face)
Sanchit Gandhi (Hugging Face)
Apolinário Passos (Hugging Face)
Pedro Cuenca (Hugging Face)