AIConnect icon

AIConnect

Use OpenAI-compatible API functions

Overview

The node "AIConnect" provides integration with OpenAI-compatible API functions, supporting multiple resources including Audio. For the Audio resource, the Create Translation operation allows users to translate audio files from one language to another using a specified AI model.

This operation is useful in scenarios such as:

  • Translating podcasts or interviews into different languages.
  • Localizing audio content for global audiences.
  • Assisting accessibility by providing translated transcripts of audio media.

For example, you can upload an English podcast episode and get a Spanish translation transcript in JSON or subtitle formats like SRT or VTT.

Properties

Name Meaning
Model The AI model used for the audio translation operation. Models are dynamically loaded via getAudioModels.
File The audio file to translate. Supported formats include flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.
Prompt Optional text to guide the model’s style or continue a previous audio segment.
Response Format The format of the translation output. Options: JSON, Text, SRT (subtitle), Verbose JSON, VTT (subtitle).
Temperature Sampling temperature controlling randomness in output. Range: 0 to 1, default 0.
Simplify Output Whether to return a simplified version of the response instead of the raw data. Default is true.
Additional Options - User A unique identifier representing your end-user, useful for tracking or personalization.

Output

The node outputs a JSON object containing the translation result of the provided audio file. The structure depends on the selected response format:

  • JSON / Verbose JSON: Detailed transcription/translation data including timestamps and confidence scores.
  • Text: Plain translated text.
  • SRT / VTT: Subtitle files formatted for video players.

If Simplify Output is enabled, the node returns a streamlined version focusing on the main translated text rather than full metadata.

No binary data output is indicated for this operation.

Dependencies

  • Requires an active connection to an OpenAI-compatible API endpoint that supports audio translation.
  • Needs an API authentication token configured in the node credentials.
  • The audio file must be accessible to the node (e.g., uploaded or referenced correctly).

Troubleshooting

  • Unsupported audio format error: Ensure the audio file is one of the supported formats (flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm).
  • Model not found or invalid: Verify that the selected model is available and correctly loaded via the dynamic options.
  • API authentication errors: Confirm that the API key credential is valid and has permissions for audio translation.
  • Timeouts or slow responses: Large audio files may take longer; consider splitting audio or increasing timeout settings if possible.
  • Empty or incomplete translations: Check the prompt and temperature settings; also verify the audio quality.

Links and References

Discussion