Basic LLM Chain cannot be used to generate audio using gemini tts model

Questions
,
1

Describe the problem/error/question

I’m trying to send text to the models/gemini-2.5-pro-preview-tts model using the Basic LLM Chain node in n8n, connected to the Google Gemini Chat Model.

There’s no way to configure the required responseModalities parameter, which results in failure.

What is the error message (if any)?

[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro-preview-tts:generateContent: [400 Bad Request] The requested combination of response modalities is not supported by the model. models/gemini-2.5-pro-preview-tts accepts the following combination of response modalities: * AUDIO

Please share your workflow

Share the output returned by the last node

[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro-preview-tts:generateContent: [400 Bad Request] The requested combination of response modalities is not supported by the model. models/gemini-2.5-pro-preview-tts accepts the following combination of response modalities: * AUDIO

Information on your n8n setup

  • n8n version: 1.93.0
  • Database (default: SQLite): SQLite
  • n8n EXECUTIONS_PROCESS setting (default: own, main): how i know?
  • Running n8n via (Docker, npm, n8n cloud, desktop app): Docker
  • Operating system: Ubuntu 24.04.2 LTS
2

I’m pretty sure an update needs to be done to make this work with n8n. I haven’t found any information if the gemini tts models work with rest api. Even the official documentation on github just includes how to setup the SDK.