elevenlabs-tts
Installation
Summary
Premium text-to-speech with 22+ voices, three quality tiers, and multilingual support across 32 languages.
- Three models available: eleven_multilingual_v2 for highest quality, eleven_turbo_v2_5 for balanced speed, and eleven_flash_v2_5 for ultra-low latency (~75ms)
- 22+ named voices across male and female personas with distinct styles (e.g., aria for conversational American, george for authoritative British)
- Fine-tune voice output via stability, similarity_boost, and style parameters; supports multiple output formats from MP3 128kbps to PCM 44.1kHz
- Covers 32 languages including English, Spanish, French, German, Chinese, Japanese, Korean, Arabic, and Hindi for global voiceover, audiobook, podcast, and accessibility workflows
SKILL.md
ElevenLabs Text-to-Speech
Premium text-to-speech with 22+ voices via inference.sh CLI.
Quick Start
Requires inference.sh CLI (
belt). Install instructions
belt login
# Generate speech with ElevenLabs
belt app run elevenlabs/tts --input '{"text": "Hello, welcome to our product demo.", "voice": "aria"}'