Smallest AIInstall

Summary

Transcribe audio binary data from a specified binary property to text using Smallest AI's speech-to-text API with optional language and detection features.

Inputs

• Binary Property (required) — Name of the binary property containing the audio file to transcribe (default 'data').
• Additional Options — Optional parameters including language (default 'en'), and boolean flags for age detection, emotion detection, and gender detection.

Output shape

a single JSON object containing the transcription text and optionally detection results, paired to the input item

The node reads audio data from the specified binary property and returns the API response JSON. If the binary property is missing, it throws an error. The output JSON includes the transcription and any enabled detection results (age, emotion, gender). The output is paired to the corresponding input item.

Examples

Example 1: Transcribe audio binary data with defaults

Set Binary Property to 'data' and leave Additional Options with default values. The node will transcribe audio as English and return transcription JSON.

Example 2: Transcribe audio with emotion and age detection

Set Binary Property to the relevant binary property name containing audio. Enable 'Emotion Detection' and 'Age Detection' in Additional Options, and specify 'language' if needed. The node outputs transcription along with emotion and age detection data.

Links

• n8n community nodes installation guide