Hi everyone ![]()
I’m trying to use the Azure Text-to-Speech API with the HTTP Request node in n8n, but I keep getting a 400 - Bad Request error.
Here’s my setup:
- Method:
POST - URL:
https://eastus.tts.speech.microsoft.com/cognitiveservices/v1 - Content-Type:
application/ssml+xml - Body: Raw SSML (confirmed valid)
- Output format:
audio-48khz-192kbitrate-mono-mp3
Headers I used:
Ocp-Apim-Subscription-Key:
set with valid keyX-Microsoft-OutputFormat:
User-Agent:n8n-clientContent-Type:application/ssml+xml
I tried both using “Generic Credential (Header Auth)” and also “None” with manual headers — still getting 400.
What’s the correct way to authenticate Azure Speech in n8n or configure credentials to allow multiple headers?
Thanks in advance ![]()
Here’s some screenshots of my node setup:


