Actions7
- Voice Actions
- Speech Actions
Overview
The Speech to Speech operation in this node converts an input audio file from one voice to another using ElevenLabs' API. It takes an audio file, processes it with a selected voice model, and outputs the converted speech in a specified audio format. This is useful for applications such as voice dubbing, creating voiceovers in different voices, or transforming recorded speech into a new voice style.
Practical examples:
- Converting a podcast episode recorded by one speaker into another speaker’s voice.
- Creating personalized voice messages by changing the voice of an existing recording.
- Generating voiceovers for videos in different character voices.
Properties
| Name | Meaning |
|---|---|
| File | The audio file to convert. Supports all major audio formats. |
| Voice | Select the voice to use for conversion. Can be chosen from a searchable list or by specifying an ID. |
| Additional Options | Collection of optional settings: |
| - Model | Select the model to use for conversion, either from a list or by ID. |
| - Output Format | Choose the output audio format and quality. Options include various MP3, PCM, ULAW, ALAW, and OPUS formats with different sample rates and bitrates. |
| - Voice Settings | JSON object to override stored voice settings, including parameters like stability, similarity boost, style, speaker boost usage, and speed. |
Output
The node outputs the converted audio data in the json field of the output item. The exact structure depends on the API response but generally includes metadata about the conversion and the audio content itself.
If binary data output is supported (typical for audio files), the node will provide the converted audio file in binary form, suitable for saving or further processing.
Dependencies
- Requires an API key credential for ElevenLabs API authentication.
- Network access to ElevenLabs API endpoint (
https://api.elevenlabs.io/v1). - Proper configuration of the API key credential within n8n.
Troubleshooting
- Invalid or missing API key: Ensure the API key credential is correctly set up and has necessary permissions.
- Unsupported audio file format: Verify that the input audio file is in a supported format.
- Voice or model not found: When selecting voice or model by ID, confirm the IDs are correct and available.
- API rate limits or quota exceeded: Check your ElevenLabs account limits if requests fail repeatedly.
- Malformed JSON in Voice Settings: If overriding voice settings, ensure the JSON is valid and parameters are within acceptable ranges.
Links and References
- ElevenLabs API Documentation (for detailed API capabilities and parameters)
- n8n Documentation (for general node usage and credential setup)