In Speech Synthesis, using the website, you can generate up to 5,000 characters in a single generation on any paid plan and up to 2,500 on all free plans.
However, if you plan on generating longer-form content of more than a few thousand characters, we highly recommend using Projects which allows you to generate extremely long-form content such as books and novels very easily. You can read more about it here.
If you're generating using the API, the maximum length of input varies depending on which model you're using:
Text-to-speech
Turbo V2 - up to 30,000 characters (~30 minutes of audio)
Multilingual V1 and V2 - up to 10,000 characters (~10 minutes of audio)
English V1 and V2 - up to 10,000 characters (~10 minutes of audio)
Speech-to-speech
Multilingual V2 - up to 10 minutes of audio
English V2 - up to 5 minutes of audio