Zhipu AI (GLM) icon

Zhipu AI (GLM)

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

Actions7

Audio Speech (TTS) → Text to Speech

AI-generated

Summary

Convert required text to speech using Zhipu’s GLM-TTS model and the selected voice. The node sends the text, voice, and optional format and speed settings to the speech API, then returns the API response in the output item’s audioData field.

Inputs

  • Model — Text-to-speech model; GLM-TTS is the only option and the default.
  • Text (required) — Text to synthesize.
  • Voice — Voice to use: Aita, Qingyi, TongTong (default), or Zhixiao.
  • Response Format — Optional output format: MP3 (default) or WAV.
  • Speed — Optional speech speed factor from 0.5 to 2; defaults to 1.

Output shape

One output item per input item, with the API response in json.audioData.

The node wraps the API response as JSON; it does not expose a separate binary audio output. With Continue On Fail enabled, a failed item instead contains json.error.

Links

Discussion