Actions5
- Text to Speech Actions
- Voice Changer Actions
- Translation Actions
- Dubbing Actions
Overview
The Voice Changer - Convert Voice operation allows users to modify the voice characteristics of an existing audio file. This node takes an input audio (either uploaded as a file or referenced via a public URL) and applies a voice transformation using a selected AI voice model. The output is a new audio file with the altered voice, which can be customized in terms of format, channel type, and sample rate.
This node is beneficial in scenarios such as:
- Creating voiceovers with different voice personas without re-recording.
- Modifying audio content for privacy or creative effects.
- Generating diverse voice samples for testing or multimedia projects.
Example use case:
A content creator wants to convert a recorded narration into a different voice style to better match a character in their video. They upload the original audio file, select a target AI voice, choose the desired output format and audio settings, and receive the transformed audio ready for use.
Properties
| Name | Meaning |
|---|---|
| Input Type | Choose whether to provide the audio as a File upload or a publicly accessible URL. |
| File | The audio file to convert. Supports all major audio formats. Shown if Input Type is "File". |
| File URL | URL of the audio file to convert. Must be publicly accessible. Shown if Input Type is "URL". |
| Voice | Select the AI voice to use for conversion. Can be chosen from a searchable list or by ID. |
| Output Format | Format of the output audio file. Options: ALAW, FLAC, MP3, ULAW, WAV. |
| Channel Type | Audio channel configuration. Options: Mono or Stereo. |
| Sample Rate | Audio sample rate in Hz. Options: 8000, 24000, 44100, 48000. |
| Encode as Base64 | Whether to receive the output audio as a Base64 encoded string instead of a URL. |
Output
The node outputs JSON data containing information about the converted audio file. Typically, this includes:
- A URL pointing to the location of the converted audio file (unless Base64 encoding is requested).
- If Encode as Base64 is enabled, the audio content is returned as a Base64 encoded string instead of a URL.
If binary data is involved, it represents the transformed audio file in the specified format and audio settings.
Dependencies
- Requires an API key credential for accessing the Murf AI service.
- The node makes HTTP requests to the Murf AI API endpoints to perform voice conversion.
- Network access must allow outbound HTTPS requests to
https://api.murf.ai. - Proper configuration of the API key credential within n8n is necessary.
Troubleshooting
Common issues:
- Invalid or missing API key: The node will fail to authenticate with the Murf AI API.
- Providing a non-public or inaccessible URL when using the URL input type will cause errors.
- Unsupported audio file formats or corrupted files may result in conversion failures.
- Selecting a voice ID that does not exist or is unavailable can cause errors.
Error messages and resolutions:
"Authentication failed": Verify that the API key credential is correctly set and valid."File not found or inaccessible": Ensure the provided URL is publicly accessible or upload a valid file."Unsupported audio format": Use a supported audio format for the input file."Voice not found": Confirm the selected voice ID exists and is available in the Murf AI voices list.