Turn any text into ready to use audio through a simple API endpoint. Ideal for marketers, video editors, and content teams who need fast, consistent voiceovers without booking talent or recording time.

A public webhook receives a POST request with two fields voice_id and text. An If node checks that both inputs exist. When valid, an HTTP Request node calls the ElevenLabs text to speech API using your API key and returns the audio file directly through the response node. If inputs are missing, the flow sends a clear JSON error. Each request can pick a different voice by passing a new voice_id, which makes this useful for many brands or languages.

Setup is simple. Create an ElevenLabs API key and add it in n8n as a custom HTTP header credential. Point your app or form to the webhook URL and send voice_id and text. Expect audio back in seconds. Teams save editing time, speed up content production, and keep tone consistent across videos, explainers, and social clips. Most users see minutes of work reduced to seconds for each script.

• POST webhook endpoint that accepts voice_id and text inputs
• Input validation with an If node to prevent bad requests
• HTTP Request to ElevenLabs text to speech API with custom header auth
• Dynamic voice selection by passing voice_id per request
• Binary response returns the audio file directly to the caller
• JSON error response when inputs are missing or invalid

• Reduce voiceover prep from 60 minutes to 2 minutes per script
• Automate up to 90 percent of repetitive voice generation tasks
• Handle 10 times more scripts without adding headcount
• Keep brand tone consistent across all audio assets
• Connect any form or app to the endpoint using standard webhooks

1. Import the template into n8n: Create a new workflow in n8n > Click the three dots menu > Select 'Import from File' > Choose the downloaded JSON file.
2. You'll need accounts with ElevenLabs. See the Tools Required section above for links to create accounts with this service.
3. In your ElevenLabs account, go to the API page and create an API key. Keep it safe as you will paste it into n8n.
4. In the n8n credentials manager, create a new HTTP Custom Auth credential. Add a header named xi-api-key and set its value to your ElevenLabs API key. Give the credential a clear name like ElevenLabs TTS Key.
5. Open the HTTP Request node named Generate voice. In Authentication, choose Generic Credential and select the HTTP Custom Auth credential you just created. Ensure the Content-Type header is set to application/json.
6. Confirm the request URL uses the voice_id variable: https://api.elevenlabs.io/v1/text-to-speech/{{ $json.body.voice_id }} and the JSON body contains the text field.
7. Open the Webhook node. Set HTTP Method to POST and confirm the path is generate-voice. Leave Response Mode set to Response Node so the workflow returns the audio.
8. Make sure the If node checks for both text and voice_id. The true path should lead to Generate voice and then to Respond to Webhook. The false path should lead to the Error response node.
9. Activate the workflow. Copy the production webhook URL shown in the Webhook node.
10. Test with curl or Postman by sending a POST JSON body like {"voice_id":"YOUR_VOICE_ID","text":"Your sample line"}. You should receive an audio file as the response.
11. If you get an Invalid inputs error, verify both fields are present and correctly named. If you see 401 from the API, check the xi-api-key value. If the voice is not found, confirm the voice_id is valid in your ElevenLabs account.
12. Monitor the execution in n8n to confirm response time and output format. Adjust text length if the service rejects very large inputs.