Sogni AI icon

Sogni AI

Generate AI images, videos, and LLM responses using Sogni AI Supernet

Actions18

Audio → Estimate Cost

AI-generated

Summary

Estimate the cost of generating audio content with a specified audio model by providing parameters such as duration, inference steps, number of tracks, and token type.

Inputs

  • Model Search — Optional string to filter audio models by name or tag, affecting the model selection dropdown.
  • Model (required) — Select or enter the ID of the audio model to use for the cost estimation.
  • Duration (Seconds) — Estimated duration in seconds of the audio to be generated (between 10 and 600 seconds). Defaults to 30.
  • Steps — Number of inference steps to use in the estimation process (1 to 200). Defaults to 30.
  • Number of Tracks — How many separate audio tracks to estimate the cost for (1 to 10). Defaults to 1.
  • Token Type — Type of token to calculate the estimate with, either 'Spark' or 'SOGNI'. Defaults to 'Spark'.

Output shape

a single record containing the estimated cost information

The output includes an object reflecting the estimated cost to generate the specified audio configuration. The node requires a valid model selection and enforces input constraints on numeric parameters.

Links

Discussion