elevenlabs-tts
Turn any text into spoken audio with ElevenLabs voices.
This skill converts text to high-quality audio files using ElevenLabs API. Use this skill when users request text-to-speech generation, audio narration, or voice synthesis with customizable voice parameters (stability, similarity boost) and voice presets (rachel, adam, bella, elli, josh, arnold, ava).
What it does
Converts any text into high-quality spoken audio using ElevenLabs’ text-to-speech API. Supports seven pre-configured voice presets with customizable parameters for stability and expressiveness.
Voice presets
- rachel (default) — clear, professional female
- adam — deep, authoritative male
- bella — warm, friendly female
- josh — friendly, conversational male
- arnold — deep, powerful male
- ava — expressive, dynamic female
- elli — young, enthusiastic female
Key features
- Tunable parameters — adjust stability (consistency vs. expressiveness) and similarity boost (adherence to voice characteristics)
- Any length — handles short phrases to full articles
- Auto-play — generated audio can be played immediately via
afplay
When to use
When you want to hear text read aloud — article narration, content preview, accessibility, or producing audio assets for podcasts and videos.