AI/ML API icon

AI/ML API

Choose from 300+ AI models, from Gemini and ChatGPT to DeepSeek and Llama.

Actions7

Audio Generation

AI-generated

Overview

This node performs audio generation using AI/ML models. It allows users to generate music or sound effects based on text prompts, with options to customize the audio format, duration, style, and other parameters. This is useful for creating custom audio content for multimedia projects, games, or creative applications.

Use Case Examples

  1. Generate a 30-second music clip in MP3 format with a specific instrument style.
  2. Create sound effects with a negative prompt to avoid certain sounds.
  3. Produce audio with a reference audio URL to guide style transfer.

Properties

Name Meaning
Model Name or ID Select the AI model to use for audio generation.
Prompt Text description of the audio or music to generate.
Extract From Response Choose which part of the audio response to return (e.g., first URL, all base64 blobs).
Audio Options Fine-tune audio generation parameters such as format, duration, style, and guidance.

Output

JSON

  • audioUrls - Array of URLs to the generated audio files.
  • audioBase64Blobs - Array of base64 encoded audio blobs.
  • rawResponse - Full raw JSON response from the audio generation API.

Dependencies

  • Requires an API key credential for the AI/ML API service to authenticate requests.

Troubleshooting

  • Common issues include invalid model selection or unsupported operation errors. Ensure the selected model supports audio generation.
  • Errors may occur if the API endpoint URL is incorrect or the API key is missing or invalid.
  • If the node returns unexpected or empty audio data, verify the prompt and audio options are correctly set and supported by the model.

Discussion