Open Apache-2.0 audio foundation model for expressive speech and multi-speaker dialogue
Higgs Audio is listed under AI Voice & Speech, in the Content & Media Generation category on Flocci AI Tools. Open Apache-2.0 audio foundation model for expressive speech and multi-speaker dialogue. It is free, with no paid plan attached, and it lives at github.com.
Higgs Audio is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 397 entries on Flocci AI Tools with no upgrade path built in.
Higgs Audio needs to be installed or self-hosted — it doesn't run in a browser tab. It is available on self-hosting and an API.
Higgs Audio does 3 things the catalog singles out: Open apache-2.0 audio foundation model for expressive speech and multi-speaker dialogue; zero-shot voice cloning and background-music-aware generation; weights on hugging face.
Copilot Audio Expressions is the closest free alternative: it sits in the same AI Voice & Speech sub-category and is free. Kokoro Web, Zonos and Chatterbox (Resemble AI) also start free. The full list is on the alternatives page.
See the full list →