Audio & Voice

Give an MCP-compatible agent access to ElevenLabs voice, speech, and audio-processing tools.

Turn text and a permitted reference clip into expressive speech using an open research implementation.

Generate expressive speech and clone a voice with detailed control over delivery.

Use text and optional audio to explore unusual sound generation and transformation.

Turn lyrics and a style direction into a complete experimental song.

Describe a musical idea and explore an AI-generated sketch in Google Labs.

Turn something you already watch, play, or read into English practice.

Turn medical dictation into a text draft with a model tuned for clinical terminology.

Turn text into expressive speech and steer delivery with natural-language audio tags.

Make and share music with AI-assisted vocals, lyrics, and beatmaking ideas.

Generate a beat, shape the arrangement, and use it under a clear license.

Turn a rough recording into a cleaner, publishable audio piece with guided editing.