Octave

A speech-language model that builds a voice from a text description or clones one from five seconds of audio, adapting to the meaning and emotion of the line. English and Spanish, about 200 ms latency.

Understands

text, 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.