Actions4
- Knowledge Database Actions
- Image Actions
- Audio Actions
- Chat Actions
Overview
The node provides transcription capabilities for audio files using AI models. Specifically, the "Audio" resource with the "Transcribe" operation allows users to convert spoken content in audio files into text. This is useful in scenarios such as generating subtitles, creating searchable transcripts of meetings or interviews, and automating note-taking from voice recordings.
For example, a user can upload an audio recording of a podcast episode and use this node to obtain a text transcript that can be published alongside the episode or used for content analysis.
Properties
| Name | Meaning |
|---|---|
| Model Name or ID | Select the AI model to transcribe the audio file. Options include "Azure: Whisper". You can also specify a model ID dynamically via expressions. |
| Options | Additional optional settings to customize transcription. |
| Language | The language code (ISO 639-1 format) of the input audio. Providing this improves transcription accuracy but is optional. |
Output
The node outputs JSON data containing the transcription results. The exact structure is not detailed in the source, but typically it would include fields such as the transcribed text and possibly metadata like confidence scores or timestamps.
No binary output is indicated for this operation.
Dependencies
- Requires an API key credential for authentication with the external AI service.
- The node communicates with an external API endpoint configured via environment variables.
- The transcription uses AI models such as "Azure: Whisper," implying dependency on Azure's speech services or similar AI providers.
Troubleshooting
Common issues:
- Incorrect or missing API key will cause authentication failures.
- Specifying an unsupported or invalid model name/ID may result in errors.
- Not providing the correct language code might reduce transcription accuracy.
- Network connectivity problems could prevent successful API calls.
Error messages:
- Authentication errors suggest checking the API key configuration.
- Validation errors related to the model parameter indicate verifying the selected model.
- If the transcription fails silently or returns empty text, ensure the audio file is correctly formatted and accessible.
Links and References
- n8n Expressions Documentation
- Azure Whisper or equivalent AI model documentation (refer to your AI provider's official docs)
- General n8n node development and usage guides at https://docs.n8n.io