You can sign in on desktop and mobile. Device and concurrent-task limits follow the current service rules.
Record about 20 seconds of clean speech, upload it on the Create Voice Model page, then select the model in Text to Speech.
Use clean speech without background music, ambient noise, other speakers or reverb. Better samples produce better results.
Console-generated files are kept for three days and API files for one day. Download generated audio promptly.
Current prices, eligibility, duration and credit amounts are returned by the service. PayPal checkout is charged in USD.
Yes. Contact customer service to confirm onboarding, credits and concurrency requirements.