Resemble Core STS v2

A speech-to-speech model that converts recorded speech into another voice, with improved pitch tracking and 48 kHz support; the target voice needs at least ten minutes of data.

Understands

audio

Produces

speech

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.