Zhipu AI (GLM) icon

Zhipu AI (GLM)

Interact with Zhipu AI (BigModel) API — Chat, Vision, Audio, Embedding, Image & Video

Actions7

Audio Transcription (ASR) → Transcribe

AI-generated

Summary

Transcribes an audio file from a URL using Zhipu’s GLM-ASR-2512 speech recognition model.

Inputs

  • Model — Speech recognition model; the only available option is GLM-ASR-2512, selected by default.
  • Audio File URL (required) — URL of the audio file to transcribe. Sent to the API as url.
  • Language — Transcription language code, such as zh or en; defaults to zh.

Output shape

One n8n item per input item, with a json object containing response with the full API response and, when the response includes it, text with the transcript.

Calls Zhipu’s audio transcription endpoint and requires Zhipu API credentials. With Continue On Fail enabled, a failed item instead contains an error field.

Links

Discussion