Turn long audio and text into ready to use content in one place. This build helps marketing and content teams make a summary, a translation, a cover image prompt, and simple HTML, all from one run.

It starts with a manual click. An audio file is read and sent to speech to text. Sample text also flows into several paths. One path creates a short tl dr summary. Another path translates the text into German. A code step builds a full message list and calls the chat API by HTTP for more control. The next step asks the model to write a prompt for an image. Then four images are created. A separate branch uses a set node and a chat step to output clean HTML with an SVG. There is also a quick reply generator for fast responses.

You need an OpenAI account and an API key. Add the key in n8n and map it to all OpenAI nodes and the HTTP request node. Then point the audio reader to your file and test each branch on its own. Teams can cut content prep time, standardize style, and ship more assets from every episode, webinar, or blog.

• Manual start to safely test each branch before full runs
• Read audio files and transcribe them using speech to text
• Create tl dr summaries with chat based prompts
• Translate content to German for multilingual reach
• Build custom message arrays in a code node and call the chat API via HTTP for full control
• Generate a DALL E prompt from the summary and create four cover images
• Produce clean HTML with an SVG using a guided chat prompt
• Generate multiple short replies for quick email responses
• Use set nodes to prepare fields and keep outputs tidy

• Reduce content prep from 2 hours to 15 minutes by automating summary, translation, and image prompt steps
• Streamline repurposing work by 70 percent with one run that outputs text, images, and HTML
• Improve consistency of tone and structure across assets by using shared prompts
• Handle more episodes or articles per week without adding staff
• Connect audio, text, and image generation in one place for easier review

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 OpenAI. See the Tools Required section above for links to create accounts with these services.
3. Create an OpenAI API key in your OpenAI account settings. Copy the key for use in n8n.
4. In n8n, open Credentials > New > search for OpenAI. Create a new credential and paste your API key. Give it a clear name like OpenAI Main.
5. Double click each OpenAI node and select your OpenAI credential from the Credential to connect with menu. If unsure, click Create new credential and follow the on screen steps.
6. Open the HTTP Request node that calls the chat API. In Authentication, select the same OpenAI credential. Confirm the model, max tokens, and temperature values.
7. Open the Read Binary Files node and set the path to a local MP3 or WAV file you want to transcribe. Keep file sizes reasonable for testing.
8. Check the Whisper transcribe node settings and confirm the model is set correctly. Run only this branch to verify transcription output.
9. Test the summary and translation path by executing the nodes after the sample text node. Adjust prompts and max tokens if results are too long.
10. Run the prompt generation and image steps. If image creation fails, reduce prompt length or lower the number of images to two.
11. Open the HTML node preview to confirm SVG and markup are valid. If HTML is messy, tighten the system message in the chat step before it.
12. When each branch works on its own, connect or run them in sequence. Save and document your prompt settings so teammates can reuse them.