Text to Speech requests are charged based on your character count, and every letter, number, punctuation mark, and space in your input text counts toward the total characters.
Several things can affect the number of characters counted for a given request:
- Pronunciation dictionaries – custom pronunciation rules applied to your text can affect the final character count.
- Tags – SSML and audio tags are counted as part of the character count for the request.
The cost of your generation is converted to credits, and the conversion rate depends on the model you're using, and whether you're generating via the website or API. For up to date pricing information, see our ElevenCreative and ElevenAPI pricing pages.