LeanVox icon

LeanVox

LeanVox TTS & STT API

Actions8

Audio → Transcribe

AI-generated

Summary

Transcribes binary audio files to text using the LeanVox API, optionally adding features like speaker diarization or a summary, and supports synchronous or forced asynchronous processing.

Inputs

  • binaryPropertyName (required) — The name of the input field containing the binary audio data (default: 'data').
  • features — Additional transcription features to enable. Options: 'diarization' (speaker identification) or 'summary'.
  • forceAsync — Whether to schedule transcription as a background job and return a job ID immediately instead of waiting for results.

Output shape

One JSON object per input item, containing the transcription result (including transcript text and optional fields like speaker labels or summary).

If 'forceAsync' is true, the response contains a job ID which can be used with the 'Check Job' operation to retrieve results later.

Examples

Example 1: Basic synchronous transcription

Input binary field: 'data'; Features: empty; Force Async: false

Example 2: Transcription with speaker diarization

Input binary field: 'audio'; Features: 'diarization'; Force Async: false

Example 3: Long-form transcription as background job

Input binary field: 'data'; Features: empty; Force Async: true

Links

Discussion