Built by Metorial, the integration platform for agentic AI.
Remove background noise from audio and isolate vocal tracks. Takes a base64-encoded audio file and returns cleaned audio with background noise, music, and ambient sounds removed.
Permanently delete a voice by its ID. Only voices you own can be deleted. This action cannot be undone.
List all available ElevenLabs AI models with their capabilities. Use this to find the right model ID for text-to-speech, voice conversion, or other operations.
Search and browse available voices with filtering, sorting, and pagination. Returns voice metadata including IDs needed for text-to-speech and other voice operations.
Create sound effects from text descriptions. Describe the desired sound using natural language or audio terminology to generate cinematic sound effects, Foley, ambient sounds, and more. Returns base64-encoded audio.
Update the default settings for a specific voice. These settings control how the voice sounds during text-to-speech generation and can be overridden per request.
Start a dubbing job to translate and voice-over audio/video content into another language. Provide a source URL and target language to begin. Returns the dubbing project ID for tracking progress.
Transcribe audio into text with high accuracy. Supports speaker diarization, word-level timestamps, and 99+ languages. Provide audio as a base64-encoded file or a publicly accessible cloud storage URL.
Retrieve current user profile and subscription details including character usage, voice slots, billing period, and plan tier.
Retrieve detailed metadata and settings for a specific voice by its ID. Includes voice properties, labels, and current settings like stability and similarity.
Browse your text-to-speech generation history. Returns metadata about past generations including the text, voice, model used, and timestamps. Use pagination to navigate through older items.
Check the status and details of a dubbing project. Use this to monitor progress of a dubbing job created with the "Create Dubbing" tool.
Convert text into lifelike speech audio using ElevenLabs voices and models. Returns base64-encoded audio that can be saved or played back. Supports multiple languages, voice customization, and various output formats.
Generate music from a text prompt describing genre, mood, style, and optionally lyrics. Returns base64-encoded audio. This is a batch operation and may take longer for longer compositions.