Skip to main content

Transcribe Audio

Transcribe audio to text using AI. Transcribe Audio node in ActionFlows. Inputs, outputs, and how to use it.

Transcribe Audio

Overview

Transcribe audio to text using AI.

Requirements

Service & Model Selection

Required for this node. Select both service and model before execution.

API Key / Credential

Required for this node. Add at least one AI provider API key/credential from Integrations.

Inputs

Standard Inputs

  • Audio Filefile · optional

    Audio file to transcribe (MP3, MP4, M4A, WAV, MPEG, MPGA, WEBM)

    Required
    No
    Multiple
    No
  • Audio URLtext · optional

    Remote audio file URL to transcribe

    Required
    No
    Multiple
    No

Outputs

  • Languagetext

    The detected language of the audio content (ISO-639-1 code, e.g. 'en')

  • Segmentsjson

    Array of transcript segments with text and timing information

  • Transcribed Texttext

    The complete transcribed text from the audio