Actions8
- Chat Actions
- Completion Actions
- Embedding Actions
- Image Actions
- Audio Actions
- Model Actions
- Moderation Actions
Audio → Transcription
AI-generatedSummary
Transcribes an audio file from the incoming item’s binary data by sending it to the LiteLLM audio transcription endpoint.
Inputs
- Model (required) — Transcription model to use; defaults to
whisper-1. - Binary Property — Name of the input binary property containing the audio file; defaults to
data. - Additional Fields: Language — Optional ISO-639-1 language code. Empty values are omitted from the request.
- Additional Fields: Prompt — Optional text to guide transcription style. Empty values are omitted from the request.
- Additional Fields: Temperature — Sampling temperature from 0 to 1; included in the request when set.
Output shape
A single item per input item, with the transcription API response as its JSON data.
Requires audio binary data under the configured property. Missing binary data raises an error; with Continue On Fail enabled, the output item contains an
errormessage andstatusCode.