Use the ElevenLabs CLI from KosmoKrator to call ElevenLabs tools headlessly, return JSON, inspect schemas, and automate workflows from coding agents, scripts, and CI.
ElevenLabs can be configured headlessly with `kosmokrator integrations:configure eleven-labs`.
# Install KosmoKrator first if it is not available on PATH.curl -fsSL https://raw.githubusercontent.com/OpenCompanyApp/kosmokrator/main/install.sh | bash# Configure and verify this integration.kosmokrator integrations:configure eleven-labs --set api_key="$ELEVEN_LABS_API_KEY" --enable --read allow --write ask --jsonkosmokrator integrations:doctor eleven-labs --jsonkosmokrator integrations:status --json
Credentials
Authentication type: API keyapi_key. Configure credentials once, then use the same stored profile from
scripts, coding CLIs, Lua code mode, and the MCP gateway.
Key
Env var
Type
Required
Label
api_key
ELEVEN_LABS_API_KEY
Secret secret
yes
API Key
url
ELEVEN_LABS_URL
URL url
no
API Base URL
Call ElevenLabs Headlessly
Use the generic call form when another coding CLI or script needs a stable universal interface.
Every function below can be called headlessly. The generic form is stable across all integrations;
the provider shortcut is shorter but specific to ElevenLabs.
eleven-labs.elevenlabs_list_voices
Read read
List available ElevenLabs voices. Returns voice names, IDs, labels, and preview URLs. Use this to discover voices for text-to-speech generation.
Generate speech audio from text using an ElevenLabs voice. Returns base64-encoded audio. Specify a voice ID and model, with optional stability and similarity boost settings.
Generate a sound effect from a text description using ElevenLabs. Returns base64-encoded audio. Describe the sound you want (e.g., "thunder rumbling in the distance").
List available ElevenLabs models. Returns model IDs, names, descriptions, and capabilities. Use this to find the right model for speech or sound generation.
Generate speech audio from text using an ElevenLabs voice. Returns base64-encoded audio. Specify a voice ID and model, with optional stability and similarity boost settings.
The model ID (e.g., "eleven_multilingual_v2"). Defaults to "eleven_multilingual_v2".
stability
number
no
Voice stability (0.0–1.0). Higher values produce more consistent, less expressive output.
similarity_boost
number
no
Similarity boost (0.0–1.0). Higher values make the output closer to the original voice.
eleven-labs.elevenlabs_generate_sound
Generate a sound effect from a text description using ElevenLabs. Returns base64-encoded audio. Describe the sound you want (e.g., "thunder rumbling in the distance").
The model ID (e.g., "eleven_sound_generation_v1"). Defaults to "eleven_sound_generation_v1".
eleven-labs.elevenlabs_list_models
List available ElevenLabs models. Returns model IDs, names, descriptions, and capabilities. Use this to find the right model for speech or sound generation.
Headless calls still follow the integration read/write permission policy. Configure read/write defaults
with integrations:configure. Add --force only for trusted automation that should bypass that policy.