ElevenLabs text-to-speech with 22+ premium voices, multilingual support, and voice tuning via inference.sh CLI. Models: eleven_multilingual_v2 (highest quality), eleven_turbo_v2_5 (low latency), eleven_flash_v2_5 (ultra-fast). Capabilities: text-to-speech, voice selection, stability/style control, 32 languages. Use for: voiceovers, audiobooks, video narration, podcasts, accessibility, IVR. Triggers: elevenlabs, eleven labs, elevenlabs tts, premium tts, professional voice, ai voice, high quality
The elevenlabs-tts skill provides high-quality text-to-speech functionality using the ElevenLabs platform, accessible through the inference.sh CLI. It allows users to convert text into natural, realistic speech in multiple languages, addressing the need for professional-grade voiceovers, accessibility tools, and audio content creation. By supporting a variety of voice options and advanced tuning parameters, it enables precise control over speech output, making it suitable for applications that demand clear, expressive, and engaging audio.
You can generate speech by using the inference.sh CLI with the command `infsh app run elevenlabs/tts --input '{"text": "Your text here", "voice": "voice_name"}'`. Make sure you are logged in to infsh before running the command.
There are three models: eleven_multilingual_v2 for highest quality, eleven_turbo_v2_5 for a balance of speed and quality, and eleven_flash_v2_5 for ultra-low latency. You can select the model using the `model` parameter in the input JSON.
You can tune voices using parameters like `stability` (0-1), `similarity_boost` (0-1), `style` (0-1), and `use_speaker_boost` (true/false) to adjust consistency, expressiveness, and style exaggeration.
The skill supports multiple output formats, including MP3 at 44.1kHz with 128kbps or 192kbps and raw PCM at 16kHz, 22.05kHz, or 24kHz. You can specify the format with the `output_format` parameter.
You need the inference.sh CLI installed and logged in on your system. Internet access is required to call the ElevenLabs API, and basic command-line familiarity is recommended.
Quick Setup:
.claude/skills/Repository
inferen-sh/skills