elevenlabs

What it does

This skill leverages the ElevenLabs API to generate realistic text-to-speech audio. It can clone voices from provided samples, allowing for highly personalized and expressive narration. The generated audio can be downloaded in various formats (mp3, wav) and controlled with parameters like speaking speed and pitch.

When to use it

• Create audiobooks or narrated presentations from written content.
• Develop voiceovers for explainer videos or marketing materials.
• Generate personalized greetings or messages using a cloned voice.
• Produce realistic dialogue for virtual assistants or interactive applications.

Key capabilities

• Voice cloning: Create replicas of existing voices based on audio samples.
• Text-to-speech generation: Convert text into spoken audio.
• Audio download: Export generated audio in MP3 and WAV formats.
• Speech parameter control: Adjust speaking speed, pitch, and other vocal characteristics.

Example prompts

• "Clone the voice from this file: [link to audio sample] and then speak the following text: 'Hello, world!'"
• "Generate audio for this script: [paste script here], using a conversational tone."
• “Read this paragraph: [paste paragraph here] at 1.2x speed with slightly higher pitch.”

Tips & gotchas

• Voice cloning requires high-quality audio samples of the target voice, ideally several minutes long for best results.
• ElevenLabs API keys are required to use this skill; ensure you have a valid key configured.