Elevenlabs

Elevenlabs MCP integration

Speaks a written reply in a chosen voice, enforces pronunciation rules for product names, dubs recordings into other languages, and reports on outbound call batches.

155actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

  • Dub a video or an audio file

    Lyro dubs a video or audio file into a target language using ElevenLabs voice technology. Support teams can localize video content for international customers, opening new markets without rerecording.

  • Convert chapter to audio

    Lyro converts the text content of a chapter into audio format for audiobook production. Agents can create audio versions of written content, making materials accessible to listeners.

  • Get user subscription info

    Lyro retrieves detailed subscription information for the currently authenticated ElevenLabs user. Support teams can check usage limits, available features, and billing status to advise customers.

See all 155 actions

How businesses use Elevenlabs + Lyro

Each card is one request a support team gets, and the Elevenlabs actions Lyro runs to close it.

  • Say the answer in the brand's own voice

    Lyro turns the written reply into audio using the voice you selected, streams it when playback should start before rendering finishes, and applies the saved settings so it sounds the same every time.

    Text to SpeechText to Speech StreamGet Voice Settings
  • Keep product names from being mangled

    Lyro loads a pronunciation dictionary from a file or from rules you dictate, and updates it when a name or a SKU changes, so the same word is not read differently on every call.

    Add Pronunciation Dictionary From RulesAdd a Pronunciation Dictionary From FileUpdate Pronunciation Dictionary
  • Dub a recording into the customer's language

    Lyro dubs an existing audio or video file, retrieves the dubbed track for a specific language, and pulls the transcript with it, so a walkthrough recorded once serves more than one market.

    Dub a Video or an Audio FileGet Dubbed Audio for a LanguageGet Dubbing Transcript by Language
  • Report what an outbound call batch actually did

    Lyro submits the batch call, reads its details while it is still running, and retries the leg that failed, so an outbound campaign is reported on rather than assumed to have completed.

    Submit Batch CallGet Batch Call DetailsRetry Batch Call

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Elevenlabs actions it has and picks the ones a request needs.

  1. 01

    Connect Elevenlabs

    Authorize the Elevenlabs account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.

  2. 02

    Tell your agent what you need

    Describe the job the way you would hand it to a teammate. Lyro maps it to the Elevenlabs actions that close it and chains as many as the request needs.

  3. 03

    Watch it work

    The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.

    Get started free
Elevenlabs · Lyro

Everything else about Elevenlabs

Setup, permissions, and the limits of what Lyro can do inside Elevenlabs.

  • They are separate surfaces, and the toolkit reaches both. Get ConvAI Agents Summaries lists the ElevenLabs agents on a workspace, Add to ConvAI Knowledge Base and Create Knowledge Base URL Document feed what they know, and Get Conversational AI Conversations reads their transcripts, so Lyro maintains and reports on them instead of duplicating them.

Every action available in Elevenlabs

All 155 actions your agent can call on Elevenlabs, straight from the live MCP connection.

  • Add a pronunciation dictionary from file

    Adds a new pronunciation dictionary from a lexicon file to improve speech synthesis accuracy.

  • Add outbound phone number

    Import/register a Twilio phone number or SIP trunk into ElevenLabs Agents Platform.

  • Add new project with attributes

    Use to create a new ElevenLabs project for text-to-speech synthesis (e.g., audiobooks); a project name is required by the API for creation, and content can be initialized using from_url or from_document.

  • Add pronunciation dictionary from rules

    Create a new pronunciation dictionary from provided rules for ElevenLabs text-to-speech.

  • Add rules to the pronunciation dictionary

    Adds one or more custom pronunciation rules (alias or phoneme) to an existing pronunciation dictionary.

  • Add sharing voice

    Adds an existing, shareable voice to a specified user's ElevenLabs account library under a new custom name, requiring the user's public ID and the voice ID.

  • Add a voice

    Adds a custom voice by uploading audio samples for voice cloning.

  • Attach phone number to agent

    Assign or unassign an existing imported phone number to an agent by updating the phone number's assigned agent.

  • Calculate convai agent llm usage

    Calculate expected number of LLM tokens needed for a conversational AI agent.

  • Calculate convai llm usage

    Calculate expected LLM usage costs for conversational AI agents.

  • Cancel batch call

    Cancel a running batch call and set all recipients to cancelled status.

  • Convert chapter to audio

    Converts the textual content of a chapter, identified by chapter_id within a project_id, into audio format.

  • Convert a project

    Converts an existing ElevenLabs Studio project, including all its chapters and using its configured settings and voices, into speech.

  • Create a previously generated voice

    Finalizes the creation of a voice using its generated_voice_id from a previous generation step by assigning a name, description, and optional labels.

  • Create conversational AI agent test

    Create a new ElevenLabs Conversational AI agent response test.

  • Add to convai knowledge base

    Add documentation to ElevenLabs Conversational AI knowledge base by uploading a file or referencing a webpage URL.

  • Create convai knowledge base file

    Create a knowledge base document from an uploaded file for ElevenLabs Conversational AI agents.

  • Create convai knowledge base folder

    Create a folder in the ElevenLabs ConvAI knowledge base for organizing documents.

  • Create convai knowledge base rag index

    Compute or retrieve RAG indexes for multiple knowledge base documents in batch.

  • Create knowledge base text document

    Create a knowledge base document with text content in ElevenLabs Conversational AI.

  • Create knowledge base URL document

    Create a knowledge base document by scraping the given webpage.

  • Create convai workspace secret

    Create a new secret for the ElevenLabs ConvAI workspace.

  • Create conversational AI tool

    Create a new conversational AI tool in ElevenLabs workspace.

  • Create conversational AI agent

    Create a new ElevenLabs Conversational AI agent with specified configuration.

  • Generate music composition plan

    Generate a music composition plan from a text prompt using ElevenLabs Music API.

  • Create an audionative enabled project

    Creates an ElevenLabs AudioNative project, generating an embeddable audio player from a provided content file using text-to-speech, allowing customization of player appearance, audio settings, and conversion options.

  • Get similar library voices

    Returns a list of shared voices similar to the provided audio sample.

  • Create single use token

    Generate a time-limited single-use token with embedded authentication for frontend clients.

  • Create workspace webhook

    Create a new webhook for the workspace with specified authentication type.

  • Delete chapter from project

    Irreversibly deletes a specific, existing chapter from an existing project, typically to remove unwanted or obsolete content.

Ready to connect Elevenlabs?

Authorize the account and your agent has all 155 actions from the first conversation.

Support agent working at a laptop next to the Lyro mascot