Technical FAQ

Find answers to common technical questions. Generally, these questions address issues related to the API and coding.


API - Error Code 400 or 401
API - Error Code 422
API - Error Code 429
Can I reduce API latency?
Do pauses and SSML phoneme tags work with the API?
How can I keep the WebSocket open?
How do I authorize myself using an API key?
How do I find the model ID?
How do I find the voice ID of my voices via the website and API?
How do I get started with the API?
How can I see information about API requests for my account?
How many Text to Speech requests can I make and can I increase it?
How much does it cost to use the API?
Is it possible to get a time stamped transcript of the audio output?
What is the Text-to-Speech WebSockets API?
What models do you offer and what is the difference between them?
Where can I learn more about API?
Why does my voice sound different in the API compared to the website?