← Model catalog

Text-to-Speech

Audio modelServed via: ByteDance Volcano ArkTier: Typical generation time: about 20s

Credit rate

This is what the site actually charges — the same formula behind the credit prompt shown before you generate.

SpecCredits
1 audio generation6

This integration charges a fixed amount for one audio generation; visual resolution tiers do not apply.

Tested limits

Taken from our own integration notes, not restated from the vendor's docs.

No special limits recorded for this model.

Templates that use this model

No templates are tuned for this model yet.

FAQ

How many credits is one audio generation on Text-to-Speech?

6 credits per audio generation. The exact cost is shown before you generate.

Do I pay separately for Text-to-Speech?

No. One Tovaki subscription covers every model in the catalog; you spend credits, not per-model subscriptions.

Can I re-run a shot on a different model?

Yes. Every shot on the canvas can be re-run on another model, and what you already generated stays.

Start with Text-to-SpeechOpen Tovaki
Text-to-Speech on Tovaki — audio generation credit rate and tested limits