Transcribe.Com
AI-generatedSummary
Transcribe audio or video file content from a binary property into text using the Transcribe.Com API, with options to specify the audio language, include timestamps, and identify speakers.
Inputs
- Binary Property (required) — The name of the binary property containing the audio/video file to transcribe, typically 'data' when coming from another node.
- Audio Language (required) — The language of the audio to assist transcription accuracy. Options include Dutch, English, French, German, Italian, Japanese, Portuguese, Russian, Spanish, and Traditional Chinese.
- With Timestamps (required) — Choose 'YES' to include timestamps in the transcription output or 'NO' to exclude them.
- With Speakers (required) — Choose 'YES' to enable speaker identification in the transcription or 'NO' to disable it.
Output shape
a single item containing a JSON object
The output JSON includes 'transcription_status' indicating the processing status and 'transcription_text' with the transcripted text. Errors related to invalid credentials, missing audio data, or insufficient credits are thrown as node errors.