ElevenLabs for AI agents
ElevenLabs generates natural-sounding AI voices and conversational agents, used by creators and developers for narration, dubbing, and voice bots across video, audio, and customer-facing applications. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in ElevenLabs.
Generate speech from text
Convert a script into natural speech audio for a video or voice application.
Add a document to an agent's knowledge base
Add a knowledge base document so a conversational agent can answer questions grounded in it.
Confirm before deleting a voice
Require approval before deleting a custom voice, since other projects may still depend on it.
155 ElevenLabs actions, graded by risk.
Every ElevenLabs action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
75Look things up. Allowed by default.
- elevenlabs.get_voiceGet voice
- elevenlabs.list_dubsList Dubs
- elevenlabs.get_modelsGet models
- elevenlabs.get_voicesGet voices list
- elevenlabs.get_chaptersGet chapters by project id
- elevenlabs.get_projectsGet projects
- elevenlabs.get_user_infoGet user info
- elevenlabs.get_agent_linkGet Agent Link
- elevenlabs.get_convai_toolGet Conversational AI Tool
- elevenlabs.get_dubbed_fileGet dubbed audio for a language
- elevenlabs.get_convai_agentGet Conversational AI Agent
- elevenlabs.get_convai_toolsGet ConvAI tools
- elevenlabs.get_agent_detailsGet agent details
- elevenlabs.get_chapter_by_idGet chapter by ID
- elevenlabs.get_project_by_idGet project by ID
- elevenlabs.get_shared_voicesGet shared voices
write
60Create and change things. Allow, or ask the user first.
- elevenlabs.add_voiceAdd a voice
- elevenlabs.add_projectAdd new project with attributes
- elevenlabs.add_sharing_voiceAdd sharing voice
- elevenlabs.create_music_planGenerate Music Composition Plan
- elevenlabs.create_convai_toolCreate Conversational AI Tool
- elevenlabs.update_convai_toolUpdate Conversational AI Tool
- elevenlabs.update_convai_agentUpdate Conversational AI Agent
- elevenlabs.create_convai_secretCreate ConvAI Workspace Secret
- elevenlabs.update_convai_secretUpdate ConvAI Workspace Secret
- elevenlabs.create_similar_voicesGet similar library voices
- elevenlabs.update_convai_settingsUpdate Convai Settings
- elevenlabs.create_single_use_tokenCreate Single Use Token
- elevenlabs.create_workspace_webhookCreate Workspace Webhook
- elevenlabs.update_workspace_webhookUpdate Workspace Webhook
- elevenlabs.add_outbound_phone_numberAdd outbound phone number
- elevenlabs.create_convai_agent_testingCreate Conversational AI Agent Test
destructive
20Delete, cancel or archive. Ask first, or deny outright.
- elevenlabs.delete_voiceDelete voice by id
- elevenlabs.delete_sampleDelete voice sample
- elevenlabs.delete_chapterDelete chapter from project
- elevenlabs.delete_projectDelete project by id
- elevenlabs.delete_mcp_serverDelete MCP server
- elevenlabs.delete_convai_toolDelete conversational AI tool
- elevenlabs.delete_convai_agentDelete Conversational AI Agent
- elevenlabs.delete_history_itemDelete history item
- elevenlabs.delete_phone_numberDelete phone number by id
- elevenlabs.delete_convai_secretDelete workspace secret
- elevenlabs.delete_dubbing_projectDelete a dubbing project
- elevenlabs.cancel_convai_batch_callCancel Batch Call
- elevenlabs.delete_workspace_webhookDelete workspace webhook
- elevenlabs.delete_convai_conversationDelete conversation by ID
- elevenlabs.delete_convai_agent_testingDelete agent response test
- elevenlabs.delete_convai_batch_callingDelete batch call
ElevenLabs in three steps.
- 01Your users connect ElevenLabsThey add their ElevenLabs api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “generate Music Composition Plan” can wait for the user, and “delete voice by id” can be denied outright.
- 03Any agent can actYour agent calls ElevenLabs through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('elevenlabs', { read: 'allow', write: 'ask', // create_music_plan destructive: 'deny', // delete_voice }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How ElevenLabs connects.
Users add their ElevenLabs api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same ElevenLabs connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use ElevenLabs from any agent.
ElevenLabs and Arc0, answered.
Can I use ElevenLabs with Claude, ChatGPT or Cursor?
Yes. Connect ElevenLabs to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the ElevenLabs actions you allow.
How do users connect ElevenLabs?
Users add their ElevenLabs api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which ElevenLabs actions can my agent take?
155 in total: 75 read, 60 write and 20 destructive, such as “generate Music Composition Plan”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in ElevenLabs?
Yes. Actions like “delete voice by id” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call ElevenLabs too?
Yes. The same ElevenLabs connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug ElevenLabs into your agent.
Your users connect ElevenLabs once, under your brand. Your agent gets 155 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan