Introducing Voicebox, a new breakthrough generative speech system based on Flow Matching, a new method proposed by Meta AI. It can synthesize speech across six languages, perform noise removal, edit content, transfer audio style & more. More details on this work & examples ⬇️

Like other generative AI work, Voicebox is able to create high-quality outputs from scratch or modify samples, but instead of images/video, it produces high-quality audio. Unlike autoregressive models, it can modify any part of a given sample — not just the end of a clip.

Voicebox generalizes across tasks and outperforms single-purpose AI models through in-context learning. It beats the previous state of the art in a number of ways. 💬 Better word error rates 🤝 Improved audio similarity ⏱️ Up to 20x faster performance

This work represents an important step forward for this field of research. Just as other work has done for images + text, we believe the generalization & scalability of Voicebox could usher in a new era of generative AI for speech — we're excited to continue pushing it forward.

Will you release source code and models We are looking forward to that Meta ai is the best with clean and easy code release Please release including fine tuning

ElevenLabs finally has a real competitor.

show code or it didnt happen

Now waiting for the code :)

Is it open source? I don't see a source release.

@YannickScholich 🔥

VOICEVOX