Limits

The following limits apply to API usage. Contact us if you need to extend them.

  • Maximum of 5 concurrent text-to-speech generations across all endpoints for one account. (Maximum of 1 for accounts on free trial.)
  • Maximum response size of 100 MB for the Bytes endpoint. Audio files will be silently truncated above this threshold. Use multiple calls to Bytes, or use the streaming endpoints, SSE and WebSocket, if you need longer audio files.
  • Maximum transcript length of approximately 5,000 characters for the Bytes endpoint. The endpoint operates under a 120-second HTTP request timeout, which limits how much audio can be generated in a single call. If your transcript exceeds 5,000 characters, use the SSE or WebSocket endpoints instead.