Use case

Music & voice
Sound for everything.

Narration in a voice that fits, your own voice cloned, transcripts of every recording, and the visuals to go with your track.

A saxophonist under amber stage light in a small jazz club, generated in OmniboMade in Omnibo

How it’s made,
in 3 steps.

Each step in its own module, shown with a real piece made in Omnibo.

01 · Voice

Find the voice

Natural speech in many voices and languages, or your own voice from a short sample.

About Voice →
02 · Voice

Transcribe it

Turn any recording into clean, timed text for captions and show notes.

About Voice →
03 · Image

Make the visuals

Cover art, a lyric video or a loop for your track, from the image and video models.

About Image →
Made in Omnibo · Seedance 2.5
The word VOYAGE in engraved lettering over a faded mapMade in Omnibo · Seedream 4.5
Made in Omnibo · Seedance 1.5 Pro

The models
people reach for.

A starting point. Every model works from the same balance.

ModelProviderRatePlanAdded
Eleven v3ElevenLabs120,000 cr / M charactersPro14 Sep 2026
Eleven Flash v2.5ElevenLabs60,000 cr / M charactersStarter14 Sep 2026
Lyria 3.5Google96 cr / clipPro13 Sep 2026
ACE-Stepfal.ai0.2 cr / secondStarter14 Sep 2026
FLUX.2 [pro]Black Forest Labsfrom 36 cr / megapixelPro9 Jun 2026

Questions,
answered.

Can I clone my own voice?

Yes. Record a short sample and use your voice for any text.

Can I make music too?

Yes. The audio models include music and sound effects as well as speech.

Your next idea
starts here.

Start free with credits every month. No card needed.

Start creating, it’s free →