What is the primary function of the Voice To Text node in an n8n workflow?
The Voice To Text node processes audio input, converting spoken language into written text using specialized transcription Integrations. The output text can then be passed to subsequent nodes for further automation, such as summarization or data entry.
Can the Voice To Text component be used as the starting point (trigger) for an automation?
No, the Voice To Text node is typically an intermediate processing step. Workflows require a specific trigger, such as a Webhook or a cloud storage service node that provides the path or URL to the audio file.
What kind of transcription Integrations does this node support?
The node supports various cloud-based Integrations, allowing you to connect to transcription services like AWS Transcribe, Google Speech-to-Text, or OpenAI Whisper. You must configure the correct credentials within the node settings.
How does this node handle multi-language transcription and identification?
The language capability depends entirely on the specific Integration configured within the node. Many supported Integrations offer automatic language identification or allow you to specify the target language before processing the audio file through the node.
What happens if the audio file exceeds the size limit defined by the API provider?
If the file is too large for the chosen API provider's limits defined in the Integrations, the node execution may fail. For very large files, you must use a service that supports long-running asynchronous jobs and structure your workflow using a separate trigger to check the status.