Text to speech models

A text to speech model reads your script aloud: a voice-over for a video, narration for a lesson or a short dialogue between two speakers. You pick the voice and the language, and some models also take direction on tone and pace. 14 models do this job in the catalog right now. Each model's page shows its form and a price guide in US dollars.

Models

Questions

How is text to speech priced?
It depends on the model: some charge per request, others by the length of the script or the audio. Each model page shows its price guide in US dollars, and the studio shows the exact price for your text before you generate. If a generation fails, the reserved amount goes back to your balance.
What do I need to write?
The script itself, exactly as it should be read. Spell out numbers and names the way they should sound, and use punctuation for pauses. The model page lists the voices, languages and other fields it accepts.
Which model should I start with?
Read the same two or three sentences of your script with a few models and voices and listen for the pronunciation of your names and terms. Once you choose a voice, keep it for every part of a longer script so it sounds like one speaker.

Other types

Found your direction?

Open the studio