AudioSeal (GGUF) is an open-source neural audio watermarking model designed for embedding and detecting imperceptible watermarks in AI-generated speech. It is robust to common audio edits and can be integrated as a backend in speech synthesis pipelines such as CrispASR. The model is intended for developers and researchers working on audio authenticity and traceability.
Audioseal is a Foundation models & chat product. It focuses on enabling robust, imperceptible watermarking of AI-generated speech for traceability and authenticity. Audioseal is an open-source project aimed at AI developers working with speech synthesis and watermarking. The project is open source (MIT). The product ships for the web and the command line.
It is developed by cstr, and the product first shipped in 2024. The project is developed in the open on GitHub with 751 stars and 1 commits in the last 90 days. Among its 5 catalogued features are audio watermarking, imperceptible embedding, and watermark detection.
Latest indexed changes and source events
cstr/audioseal-GGUF verified by the PulseGate indexer
Other apps tracked under the same category.
