voice isolator
inworld · Nov 14, 2026
voice isolator is a audio-to-audio model published on Hugging Face by inworld.
Open-weight modelapache-2.0
sava is a voice-activity-detection model published on Hugging Face by inworld.
inworld/savasava is an open-weight model from inworld, released on Nov 14, 2026, with the apache-2.0 license.
Specs are sourced from Hugging Face and were last checked on Nov 20, 2026. Always confirm current pricing and limits with the provider before production use.
sava was published on Nov 14, 2026.
sava is published as an open-weight model on Hugging Face under the apache-2.0 license, so you can download the weights and run them on compatible hardware, subject to the license terms.