Choose the voice and format that fit your narration.
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
Select a voice and create speech with timing metadata for the supplied text.
/oo ElevenLabs: Find an ElevenLabs voice matching [voice criteria]. Use selected voice ID [ID] to synthesize [text] in [format] with character timing. Provide the audio file link and timing metadata for editing.
Create an audio effect from a descriptive prompt.
/oo ElevenLabs: Generate an ElevenLabs sound effect for [scene and sound description], lasting [duration up to 30 seconds], in [format]. Use looping [yes/no] and provide the audio file link.
Set up oo CLI and the oo Skill in your agent.
Install OOMOL →Connect with an ElevenLabs API key.
Connect ElevenLabs →Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →Choose Your Agent
Browse voices and speech models, generate narration with optional character timing, and create sound effects from text. Audio outputs are uploaded to connector transit storage so they can be accessed through file links.
Inspect available voices, their settings and speech model capabilities.
Generate speech and effects or retrieve an existing history item’s audio.
Get the current ElevenLabs user profile together with the embedded subscription snapshot.
Leina 
Wanta 
elevenlabs.get_user_info Get the current ElevenLabs subscription details for the authenticated user.
elevenlabs.get_user_subscription_info List the available ElevenLabs models and their text-to-speech capabilities.
elevenlabs.get_models List the available ElevenLabs voices with their key metadata and settings.
elevenlabs.get_voices Get one ElevenLabs voice by voice ID, with optional settings included.
elevenlabs.get_voice Search ElevenLabs voices with v2 pagination, filtering, sorting, and optional total count.
elevenlabs.search_voices Get the synthesis settings configured for one ElevenLabs voice.
elevenlabs.get_voice_settings List generated ElevenLabs history items with pagination and optional voice filtering.
elevenlabs.get_generated_items Get one ElevenLabs history item by history item ID without downloading its audio.
elevenlabs.get_history_item_by_id Generate speech audio from text by calling ElevenLabs text-to-speech and uploading the binary result to connector transit storage.
elevenlabs.text_to_speech Generate speech audio with character-level timing, upload the audio to connector transit storage, and return timing metadata.
elevenlabs.text_to_speech_with_timestamps Generate a sound effect from a text prompt and upload the binary audio result to connector transit storage.
elevenlabs.create_sound_effect Download the audio for one ElevenLabs history item and upload the binary result to connector transit storage.
elevenlabs.get_audio_from_history_item Delete one ElevenLabs history item by history item ID.
elevenlabs.delete_history_item No matching tools.
Give your team the generated audio and script to review together.
An audio file link plus character-level timing metadata. Use the timing alongside the original text when preparing an edit or alignment.
List generated history items, select a history item ID and request its audio. The download is also placed in transit storage.
Search by your criteria and inspect the selected voice’s metadata and settings. Supply its voice ID when requesting synthesis.
Manage which optional storage OOMOL can use. You can change these choices from the footer at any time.
