Tool
Add voice
ElevenLabs Add Voice is a powerful AI tool designed to create custom voices by uploading one or more audio files. It enables seamless voice cloning and personalization, enhancing audio experiences for a variety of applications.
Features
- Upload multiple audio files to generate a unique custom voice.
- Easy integration with ElevenLabs API for streamlined workflows.
- Supports descriptive metadata to label and characterize each voice.
- User-friendly interface to name and identify voices in dropdown menus.
- High-quality voice synthesis ensuring natural and clear audio output.
Benefits
- Create personalized voice models for branding and content creation.
- Enhance user engagement with realistic and diverse voice options.
- Save time and resources compared to traditional voice recording methods.
- Facilitate accessibility by generating voices suited for different audiences.
- Improve audio project versatility with customized voice assets.
Description
Add a voice from one or more audio files. See the documentation
IMPORTANT: The arguments have specific formats. Please follow the instructions below:
- files: Return JSON in this format: string[]
Parameters
4 parameters
| Name | Type | Description |
|---|---|---|
| namerequired | string | The name that identifies this voice. This will be displayed in the dropdown of the website. |
| filesrequired | string[] | Provide either an array of file URLs or an array of paths to a files in the /tmp directory (for example, /tmp/myFile.pdf). |
| description | string | How would you describe the voice? |
| labels | string | Serialized labels dictionary for the voice. |
