Hi all, I am using the Live Translate API and I really like the voice recognition and replication features. However, I would love a way to define a specific, consistent voice so it doesn’t shift or change as much when the speaker pauses for too long. Is this somehow possible, and are there any new features coming to this API soon?
Hello @darikletter While we cannot comment on unannounced roadmap items or future feature releases, we continuously update our platform capabilities. You can monitor upcoming changes, new features, and model improvements by keeping an eye on our official Release Notes and Updates and the Live Translate Documentation