ai
ElevenLabs CLI for Shell Scripts
Use the ElevenLabs CLI for shell scripts with headless JSON commands, schema discovery, credentials, and permission controls.
8 functions 5 read 3 write API key auth
ElevenLabs CLI for Shell Scripts
Call integration functions from shell scripts with stable JSON input and output.
Use shell scripts for small local automations that need one or more integration calls. The ElevenLabs CLI uses the same integration registry as the TUI, Lua runtime, and MCP gateway, but returns predictable command output for automation.
Command Shape
# ElevenLabs CLI for Shell Scripts
kosmokrator integrations:configure elevenlabs --set api_key="$ELEVENLABS_API_KEY" --enable --read allow --write ask --json
kosmo integrations:call elevenlabs.elevenlabs_text_to_speech '{"voice_id":"example_voice_id","text":"example_text","model_id":"example_model_id","stability":1,"similarity_boost":1,"style":1,"use_speaker_boost":true}' --json Discovery Before Execution
Agents and scripts can inspect ElevenLabs docs and schemas before choosing a function.
kosmo integrations:docs elevenlabs --json
kosmo integrations:docs elevenlabs.elevenlabs_text_to_speech --json
kosmo integrations:schema elevenlabs.elevenlabs_text_to_speech --json
kosmo integrations:search "ElevenLabs" --json
kosmo integrations:list --json Useful ElevenLabs CLI Functions
| Function | Type | Parameters | Description |
|---|---|---|---|
elevenlabs.elevenlabs_text_to_speech | Write | voice_id, text, model_id, stability, similarity_boost, style, use_speaker_boost | Convert text to speech audio using an ElevenLabs voice. Returns base64-encoded audio. Choose a voice ID and model ID to control the output. |
elevenlabs.elevenlabs_list_voices | Read | none | List all available voices in your ElevenLabs account, including pre-made and cloned voices. Use this to discover voice IDs for text-to-speech. |
elevenlabs.elevenlabs_get_voice | Read | voice_id | Get detailed information about a specific ElevenLabs voice, including its settings, labels, and fine-tuning info. |
elevenlabs.elevenlabs_create_voice | Write | name, files, description | Create a new voice clone in ElevenLabs. Provide a name, optional audio sample file paths or base64-encoded data, and an optional description. |
elevenlabs.elevenlabs_delete_voice | Write | voice_id | Permanently delete a voice from your ElevenLabs account. This action cannot be undone. |
elevenlabs.elevenlabs_get_models | Read | none | List all available ElevenLabs text-to-speech models, including their IDs, names, and language support. Use model IDs when calling text_to_speech. |
elevenlabs.elevenlabs_get_history | Read | page_size, start_after | Browse your ElevenLabs generation history. Returns a paginated list of past text-to-speech requests with metadata. |
elevenlabs.elevenlabs_get_current_user | Read | none | Get your ElevenLabs account details, including subscription tier, character usage, and remaining quota. |
Automation Notes
- Use
--jsonfor machine-readable output. - Keep credentials out of argv by using environment variables or stored KosmoKrator configuration.
- Configure read/write policy before unattended runs; use
--forceonly for trusted automation. - Use the MCP gateway instead when the agent needs dynamic tool discovery inside a conversation.