How billing works
Requests to the/diarize and /identify API endpoints are billed based on the audio duration in seconds that is sent for processing.
Requests to /voiceprint are billed per voiceprint created rather than by audio duration.
If transcription is enabled on /diarize, the request is billed at the transcription price shown as STT Orchestration in our plans. You still receive diarization segments as part of the output at no additional cost.
Minimum charge
There is a 20-second minimum charge for all requests to
/diarize and /identify. If you send a request with an audio file that is less than 20 seconds, the request is billed as 20 seconds.- An 8-second
/diarizerequest is billed as 20 seconds - A 20-second
/identifyrequest is billed as 20 seconds - A 182-second
/diarizerequest is billed as 182 seconds - A
/voiceprintrequest is billed per created voiceprint
What can affect cost
- The endpoint you use
- The model that was selected
- The audio duration in seconds for
/diarizeand/identify - Whether you requested transcription with a
/diarizerequest
/diarize, the STT Orchestration price applies. For your current pricing, use the plan page in the dashboard as the source of truth.