👉 n8n No Limits Access :

https://www.hostg.xyz/SHHAd

Hébergement VPS n8n | Automatisation sécurisée et évolutive

coupon -15% : DRFIRAS15

👉 Formation n8n en Français

Formation n8n en Français : Automatisation & Agents IA

coupon -20% : LANCEMENT : HERE

Overview

This workflow turns a message typed into the n8n Chat into a ready-to-play sound effect. An OpenAI model acts as a "sound-effects director": it rewrites the user's casual description into a literal, detailed prompt and picks sensible generation settings. A Code node then clamps those settings to safe ranges before calling the ElevenLabs sound-generation API. The generated MP3 is attached directly to the chat reply as binary data — there is no Google Drive, S3, or other external storage step, which keeps the template simple and free of extra credentials.

Flow at a glance

flowchart LR
    A["Chat Trigger<br/>When Chat Message Received"] --> B["Basic LLM Chain<br/>Compose Sound Effect Prompt"]
    M["OpenAI Chat Model<br/>OpenAI Sound Director Model"] -.model.-> B
    B --> C["Code<br/>Clamp Sound Settings"]
    C --> D["HTTP Request<br/>Generate Sound With ElevenLabs"]
    D -->|success| E["Set<br/>Reply In Chat With Sound"]
    D -->|error| F["Set<br/>Report Sound Failure"]
    B -.error output.-> C

Prerequisites & credentials

<aside> 🔑

You need two credentials before building this workflow:

  1. OpenAI account (type: OpenAI API) — used by the sound-director model.
  2. ElevenLabs API (type: Header Auth) — used by the HTTP Request node that calls ElevenLabs. </aside>

1. OpenAI credential

2. ElevenLabs credential