Actions15
- Audio Actions
- Document Actions
- File Search Actions
- Image Actions
- Media File Actions
- Text Actions
- Video Actions
Audio → Analyze Audio
AI-generatedSummary
Analyze audio content with a specified text prompt using a selected Gemini audio model.
Inputs
- Model (required) — Select the Gemini audio model to use for analysis, either from a searchable list or by specifying its ID.
- Text Input — Enter a text prompt guiding the analysis, defaulting to 'Summarize this audio'.
- Input Type (required) — Choose whether to provide audio via URLs or binary files.
- URL(s) — Provide comma-separated URLs of audio files (if Input Type is 'Audio URL(s)').
- Input Data Field Name(s) — Specify the name(s) of binary data fields containing audio to analyze (if Input Type is 'Binary File(s)').
- Simplify Output — Toggle to simplify the response output for easier consumption.
- Options — Configure additional options such as maximum token length for the analysis description.
Output shape
a list of candidate responses per input item
Returns either simplified individual candidate items or the full API response per input item, depending on the 'Simplify Output' setting.