Elevenreader
ElevenReader is an AI-powered text-to-speech application by ElevenLabs that converts written content into natural-sounding audio
Verdict
Common use cases
- Generate podcast narration from show notes
- Test pronunciation tweaks before recording
- Clone a voice from sample audio
- Estimate LLM costs for a conversational agent
- Add documentation to an AI agent's knowledge base
Integration
- Vendor
- Elevenreader
- Category
- other
- Auth
- API_KEY
- Tools
- 50
- Composio slug
elevenreader
Tools
- Add Documentation To Knowledge Base
Tool to add documentation to a conversational AI agent's knowledge base. Accepts either a file upload or a URL to documentation. Use when configuring an agent to have access to specific documentation for user interactions.
- Add Pronunciation Dictionary From File
Tool to add a pronunciation dictionary from a .pls file to ElevenLabs. Use when you need to create custom pronunciation rules for text-to-speech.
- Add Pronunciation Dictionary From Rules
Tool to add a pronunciation dictionary from rules in ElevenLabs. Use when you need to define custom pronunciations for text-to-speech using alias rules (text replacements) or phoneme rules (phonetic pronunciations).
- Add Pronunciation Dictionary Rules
Tool to add pronunciation rules to an ElevenLabs pronunciation dictionary. Use when you need to customize how specific words or phrases are pronounced in text-to-speech, either by providing an alias (alternative text) or phoneme representat
- Add Shared Voice
Tool to add a shared voice from another user's public library to your own voice library. Use when you want to clone or use a voice that has been shared publicly by another ElevenLabs user.
- Add Tool
Tool to add a conversational AI tool to ElevenLabs ConvAI. Use when you need to create a new tool for agents to use during conversations. Supports webhook, client-side, system, and MCP tools.
- Calculate Agent LLM Expected Cost
Tool to calculate expected LLM usage costs for a conversational AI agent. Use when estimating operational costs based on knowledge base size, prompt length, and RAG configuration.
- Calculate Public LLM Expected Cost
Tool to calculate expected LLM usage costs based on prompt length, knowledge base size, and RAG configuration. Use when estimating operational costs for conversational AI without requiring a specific agent.
- Cancel batch call
Tool to cancel an active batch call operation. Use when you need to stop a scheduled or in-progress batch calling campaign.
- Compute RAG Index
Tool to compute RAG index for a knowledge base document. Use when you need to generate embeddings for a specific document to enable semantic search and retrieval.
- Create Agent
Tool to create a conversational AI agent with ElevenLabs. Use when you need to set up a new agent with specific voice, language, and conversation settings.
- Create Agent Response Test
Tool to create an agent response test for testing conversational AI agents. Use when you need to create response tests, tool call tests, or simulation tests for agent validation.
- Create Audio Native Project
Tool to create an Audio Native enabled project on ElevenLabs. Use when you need to convert text or HTML content into an embeddable audio player with customizable appearance and voice settings.
- Create Batch Call
Tool to submit a batch call request to ElevenLabs ConvAI. Use when you need to initiate automated calls to multiple recipients with a conversational AI agent.
- Create Convai Workspace Secret
Tool to create a Convai workspace secret in ElevenLabs. Use when you need to securely store API keys, tokens, or other sensitive values for agent workflows.
- Create File Document
Tool to create a file document in the ElevenLabs knowledge base. Use when you need to upload documentation that the agent will access for user interactions.
- Create Folder
Tool to create a folder in the ElevenLabs knowledge base. Use when you need to organize documents into folders for better structure and management.
- Create Text Document
Tool to create a text document in the ElevenLabs knowledge base. Use when you need to add text content that the agent will access for user interactions.
- Create URL Document
Tool to create a URL document in the ElevenLabs knowledge base. Use when you need to add web-based documentation that the agent will access for user interactions.
- Delete Agentdestructive
Tool to permanently delete an agent from ElevenLabs. Use when you need to remove an agent that is no longer needed.
- Delete Agent Response Testdestructive
Tool to delete an agent response test. Use when you need to remove a test that is no longer needed.
- Delete Batch Calldestructive
Tool to delete a specific batch call. Use when you need to permanently remove a batch call by its ID. The batch call ID must be valid and the batch call must exist, otherwise a 404 error will be raised. Example: "Delete batch call with ID b
- Delete Convai Workspace Secretdestructive
Tool to delete a specific Convai workspace secret. Use when you need to permanently remove a secret by its ID.
- Delete Conversationdestructive
Tool to delete a conversation by its unique ID. Use when you need to permanently remove a conversation from the system.
- Delete Dubbingdestructive
Tool to permanently delete a dubbing project by its ID. Use when you need to remove a dubbing project that is no longer needed.
- Delete Knowledge Base Documentdestructive
Tool to permanently delete a document from the knowledge base. Use when you need to remove documentation that is no longer needed.
- Delete Phone Numberdestructive
Tool to permanently delete a phone number from ElevenLabs ConvAI. Use when you need to remove a phone number that is no longer needed.
- Delete RAG Indexdestructive
Tool to permanently delete a RAG index from a knowledge base document. Use when you need to remove an embedding index that is no longer needed.
- Delete Speech History Itemdestructive
Tool to permanently delete a speech history item by its ID. Use when you need to remove a specific history item from ElevenLabs.
- Delete Tooldestructive
Tool to permanently delete a conversational AI tool from ElevenLabs. Use when you need to remove a tool that is no longer needed.
- Delete Transcript By Iddestructive
Tool to permanently delete a speech-to-text transcript by its ID. Use when you need to remove a transcript that is no longer needed.
- Download Speech History Items
Tool to download speech history items from ElevenLabs. Use when you need to retrieve previously generated audio files. Returns a single audio file or a zip containing multiple files.
- Duplicate Agent
Tool to duplicate an existing agent. Use when you need to create a copy of an agent with all its configuration.
- Edit Voice
Tool to edit an existing voice in ElevenLabs. Use when you need to update a voice's name, description, labels, or add audio files to it.
- Edit Voice Settings
Tool to edit voice settings for a specific voice in ElevenLabs. Use when you need to adjust voice parameters like stability, similarity boost, speed, style, or speaker boost.
- Generate Composition Plan
Tool to generate a music composition plan using ElevenLabs Music API. Use when you need to create a structured musical composition from a text prompt, including style directions and song sections.
- Get agent
Tool to retrieve complete details for a specific conversational AI agent by ID. Use when you need agent configuration, workflow, platform settings, or metadata.
- Get Agent Knowledge Base Size
Tool to retrieve the size of a conversational AI agent's knowledge base. Use when you need to check how many pages are stored in an agent's knowledge base.
- Get Agent Response Test
Tool to retrieve agent response test details by test ID. Use when you need to fetch test configuration and parameters.
- Get Agent Response Tests Summaries
Tool to retrieve agent response test summaries by test IDs. Use when you need to fetch summary information for specific agent tests.
- Get Agent Shareable Link
Tool to get a shareable link for a conversational AI agent. Use when you need to generate or retrieve a link to share an agent with others.
- Get Agent Summaries
Tool to retrieve summaries for multiple agents by their IDs. Use when you need to fetch agent information for one or more agents. The response includes a dictionary keyed by agent ID, where each value indicates success or failure for that s
- Get Agent Widget Config
Tool to retrieve the widget configuration for a conversational AI agent. Use when you need to get the embed/widget settings including appearance, behavior, and interaction options.
- Get Audio From History Item
Tool to retrieve the audio file from a speech history item. Use when you need to download the generated audio for a specific history item.
- Get Audio Native Project Settings
Tool to retrieve audio native project settings from ElevenLabs. Use when you need to get configuration details for a specific Studio project, including enabled status, project settings (title, author, colors, etc.), and snapshot information
- Get Batch Call By Id
Tool to retrieve a batch call by its ID. Use when you need to check the status and details of a specific batch call.
- Get ConvAI dashboard settings
Tool to retrieve ConvAI dashboard settings including configured charts. Use when you need to view dashboard configuration or check which charts are enabled.
- Get conversation history
Tool to retrieve complete conversation details including transcript, metadata, and analysis. Use when you need to examine the full conversation history, timing data, or assess call performance.
- Get Conversations
Tool to retrieve conversations from ElevenLabs Conversational AI. Use when you need to list, filter, or search conversations by various criteria such as agent, date range, rating, or language.
- Get Conversation Signed Link
Tool to get a signed URL for a conversation with an agent. Use when you need to generate a secure URL for accessing a conversation.
Setup
Setup guide
- 11. In Switchy, open Settings → Integrations → MCP Servers and click Add Server. 2. Select Elevenreader from the list and choose API Key authentication. 3. Log into your ElevenLabs account, navigate to Profile → API Keys, and generate a new key (or copy an existing one). 4. Paste the key into Switchy and click Connect. 5. Switchy will verify the key and list available tools — you should see options like 'Add Pronunciation Dictionary From Rules' and 'Add Tool'. 6. Open any Space, type '@Elevenreader list my voices' and send — if the MCP replies with your voice library, the connection works. 7. To invoke a tool, @mention Elevenreader and describe what you need (e.g. '@Elevenreader generate speech from this script using my default voice'). 8. If a tool requires file input (like adding a .pls pronunciation dictionary), attach the file to your message before sending.
What teammates see: by default, memories from Elevenreader are scoped to the Space (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Spaces have used this MCP together with a given model.
How Switchy teams use it
Starter prompts
Generate Speech Sample
@Elevenreader generate speech from the following text using my default voice: 'Welcome to the weekly product update. This week we shipped three new features and resolved 12 customer-reported bugs.'Open in a Space →
Add Pronunciation Rule
@Elevenreader add a pronunciation rule to my dictionary so 'Switchy' is pronounced as 'SWICH-ee' (phonetic: ˈswɪtʃi) in all future speech generation.Open in a Space →
Estimate Agent Costs
@Elevenreader calculate the expected LLM cost for an agent with a 50-page knowledge base, average prompt length of 200 tokens, and RAG enabled.Open in a Space →
Add Knowledge Base Docs
@Elevenreader add the documentation at https://docs.example.com/api-reference to my customer support agent's knowledge base.Open in a Space →
Clone Shared Voice
@Elevenreader add the shared voice with ID 'abc123xyz' from the public library to my voice collection.Open in a Space →
Example outputs
Illustrative - representative of the model's voice and quality, not literal recordings.
@elevenreader add our API documentation from https://docs.company.com/api to the customer-support agent's knowledge base
Documentation successfully added to the customer-support agent's knowledge base. The system ingested 47 pages covering authentication, endpoints, rate limits, and error codes. The agent can now answer technical questions about your API using this reference material. Knowledge base processing typically takes 2-3 minutes before the agent can query the new content effectively.
This example shows the MCP's core documentation-ingestion capability. The agent won't have access to the new knowledge immediately — there's a processing delay. You'll need valid API credentials and the target agent must already exist in your ElevenLabs account before adding documentation.
@elevenreader create a pronunciation dictionary that says 'SQL' as 'sequel' and 'API' as 'A-P-I' for our product demo voice
Pronunciation dictionary created with 2 alias rules: 'SQL' → 'sequel' and 'API' → 'A-P-I'. Dictionary ID: pron_abc123def456. You can now attach this dictionary to any voice in your library to ensure consistent pronunciation in text-to-speech output. These rules apply only when the dictionary is explicitly linked to a voice — they won't affect other voices automatically.
Demonstrates custom pronunciation control for text-to-speech workflows. The dictionary exists independently and must be manually attached to each voice that should use it. Useful when your content includes technical terms, brand names, or acronyms that default TTS engines mispronounce.
@elevenreader estimate the monthly LLM cost for running our sales-assistant agent with a 15,000-token knowledge base and RAG enabled
Estimated monthly LLM cost for the sales-assistant agent: $127–$156, assuming 10,000 conversations per month with an average of 8 turns each. This estimate accounts for the 15,000-token knowledge base, RAG retrieval overhead (approximately 2,000 tokens per query), and typical prompt/completion lengths. Actual costs vary based on conversation complexity and user query length.
This calculation tool helps forecast operational expenses before deploying a conversational agent at scale. The estimate assumes moderate usage patterns — high-volume or long-running conversations will increase costs. RAG-enabled agents incur additional token overhead for each knowledge base query, which this estimate includes.
Use-case deep-dives
When Elevenreader makes sense for a 3-person support team
A small SaaS company with three support reps wants to offload tier-1 questions to a voice agent that can read from their help docs and product guides. Elevenreader wins here because it bundles the knowledge-base ingestion (Add Documentation To Knowledge Base from URL or file) with the pronunciation tuning (pronunciation dictionaries for product names) and cost estimation (Calculate Agent LLM Expected Cost) in one MCP. The team uploads their Notion export, adds a few phoneme rules for brand terms, and gets a working conversational agent without stitching together three separate services. The threshold: if your docs change daily or you need sub-100ms latency, you'll outgrow this fast. For a stable help center and a team that wants one integration instead of five, Elevenreader is the right call.
Why Elevenreader isn't built for batch video workflows
A 6-person product marketing team ships 20 onboarding videos a quarter and wants to automate the voiceover step. Elevenreader's conversational-agent focus (tools like Add Tool, Add Shared Voice) suggests it's optimized for real-time dialogue, not batch rendering. The pronunciation dictionaries help with brand consistency, but the MCP doesn't expose batch-job primitives or render queues—you're calling text-to-speech in a conversational loop, not a video pipeline. If your workflow is 'generate script, render audio, drop into Premiere,' you want ElevenLabs' direct API or a dedicated TTS MCP, not this conversational wrapper. Elevenreader shines when the voice output is interactive; for pre-recorded content at volume, it's the wrong tool.
When Elevenreader fits a 10-person distributed team's Slack bot
A remote startup with 10 employees wants a Slack bot that answers policy questions, reads from the employee handbook, and pronounces founder names correctly. Elevenreader's knowledge-base tools (Add Documentation To Knowledge Base) let the ops lead upload the handbook once, the pronunciation dictionaries handle the founder-name edge cases, and the cost calculator (Calculate Agent LLM Expected Cost) keeps the CFO happy before launch. The conversational-agent framing matches the use case: employees ask questions in natural language, the bot responds with voice or text. The trade-off: if the handbook lives in Google Docs and updates weekly, the manual re-upload loop gets old. For a static or slow-changing knowledge base and a team that wants voice-first answers, Elevenreader is a clean fit.
Frequently asked
What does the Elevenreader MCP do in Switchy?
It connects your Switchy workspace to ElevenLabs' text-to-speech and conversational AI platform. You can manage voice libraries, add pronunciation dictionaries, configure AI agents with knowledge bases, and estimate LLM costs — all without leaving Switchy. Useful if your team builds voice apps or conversational agents and needs to coordinate ElevenLabs configuration across projects.
Do I need an ElevenLabs paid plan to use this MCP?
You need an ElevenLabs API key, which typically requires a paid subscription. Free-tier keys have rate limits that may block some MCP operations. The MCP uses API_KEY auth, so whoever connects it must have access to your organisation's ElevenLabs API credentials. Check your ElevenLabs dashboard under Profile → API Keys to confirm access level.
Can this MCP generate speech audio files directly?
No. The Elevenreader MCP focuses on configuration and management — adding voices, setting pronunciation rules, building agent knowledge bases, estimating costs. It doesn't expose the core text-to-speech synthesis endpoint. If you need to generate audio, use ElevenLabs' API directly or their web interface. This MCP is for the setup work, not the production output.
How is this different from just using the ElevenLabs dashboard?
The dashboard is faster for one-off tasks. This MCP matters when you're coordinating voice work across multiple Switchy projects or automating repetitive setup — like bulk-adding pronunciation rules or syncing agent knowledge bases. It also lets non-technical team members trigger ElevenLabs config changes from Switchy without needing dashboard access or API knowledge.
Who on the team should connect the Elevenreader MCP?
Whoever owns your ElevenLabs account and has API key access. Typically a product lead or engineer managing voice infrastructure. Once connected in Switchy, other team members can invoke the tools without needing their own ElevenLabs credentials. The MCP doesn't count against Switchy seat limits, but ElevenLabs API usage follows your ElevenLabs plan quotas.