🚀 It's go time! XTTS Release 🚀

First release set the bar for quality✨now we’re setting the bar for size and speed 🏎️

✅ 3090 GPU
140ms streaming latency 🤯
0.1 Real-Time Factor 🤯

✅ Macbook CPU
1.7 Real-Time Factor 😎

Live now on @huggingface 🔥

hf.co/spaces/coqui/X… 🎧 Say hello to Hifigan! 🎶

Coqui has upgraded to a super-efficient hifigan, enhancing audio quality and reducing memory load.

For the first time, CPU inference is possible 🚀

Plus, enjoy smoother performance on smaller GPUs (only needs 4G VRAM) 🤯

github.com/coqui-ai/TTS

👋 Hi, we're Coqui :)

Open speech tech 🐸💬 is our mission 🚀

💚 Join the community
👩‍💻 Use the tech
💪 Share the power

Leave a 🌟 on Github for new models and releases!

github.com/coqui-ai next-level Text-to-Speech is now as easy as 𝚙𝚒𝚙 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 𝚃𝚃𝚂 🚀

Get the latest outputs from ML research, in production-ready code.

Leave a 🌟 on 🐸TTS for new models and releases!

github.com/coqui-ai/tts