Integration

ElevenLabs integration

AI voice synthesis and cloning platform for realistic text-to-speech generation. Create natural-sounding voiceovers, clone voices with minimal samples, generate multilingual speech, and build conversational voice agents. Perfect for audiobooks, dubbing, accessibility features, and interactive voice applications.

Connect ElevenLabs How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in ElevenLabs.Built from the 60 ElevenLabs tools below, on the connection you add once.

Common ElevenLabs use cases

Build voice assistants
Check conversion status
Improve clone quality
Rename voice
View all agents
View chapter list
Remove bad samples
Save designed voice
Transcribe podcasts
Real-time captioning

What you can do with ElevenLabs

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Voice, 16 operations

add_shared_voiceAdd shared voicePOSTAdds a shared voice from the voice library to your personal voice collection.
add_voiceAdd voicePOSTCreates a custom AI voice clone from audio samples for personalized speech synthesis.
create_voice_from_previewCreate voice from previewPOSTCreates a permanent voice from a generated voice preview.
delete_voiceDelete voiceDELETEPermanently removes a custom cloned voice from the account and makes it unavailable for synthesis.
delete_voice_sampleDelete voice sampleDELETEDeletes a specific audio sample from a cloned voice.
design_voiceDesign voicePOSTGenerates voice preview samples from a text description for creating custom AI voices.
edit_voiceEdit voicePOSTUpdates an existing voice's name, description, labels, or adds new audio samples.
edit_voice_settingsEdit voice settingsPOSTUpdates the default voice settings for a specific voice model.
get_shared_voicesGet shared voicesGETRetrieves shared voices from the ElevenLabs voice library marketplace.
get_similar_voicesGet similar voicesPOSTFinds voices in the library that are similar to a provided audio sample.
get_voiceGet voiceGETFetches detailed information about a specific voice including settings, samples, and metadata.
get_voice_sample_audioGet voice sample audioGETDownloads the audio file for a specific voice sample.
get_voice_settingsGet voice settingsGETRetrieves the default voice settings configured for a specific voice model.
list_voicesList voicesGETRetrieves all available voice models including premade, cloned, and shared voices with detailed characteristics.
remix_voiceRemix voicePOSTTransforms an existing voice by modifying its characteristics through text prompts.
search_voicesSearch voicesGETSearches and filters available voices with advanced filtering and pagination support.

Audio, 7 operations

audio_isolationAudio isolationPOSTSeparates and extracts clean voice audio from recordings containing background noise and music.
speech_to_speechSpeech to speechPOSTTransforms input speech into different voice while preserving prosody, emotion, and speaking style from the original audio.
speech_to_speech_streamSpeech to speech streamPOSTStreams voice conversion output in real-time for low-latency voice transformation.
text_to_speechText to speechPOSTConverts text to natural-sounding speech using AI voice synthesis with advanced customization controls for voice characteristics.
text_to_speech_streamText to speech streamPOSTStreams text-to-speech audio in real-time for low-latency playback without waiting for complete generation.
text_to_speech_stream_with_timestampsText to speech stream with timestampsPOSTStreams text-to-speech audio with real-time timestamps for each character.
text_to_speech_with_timestampsText to speech with timestampsPOSTGenerates speech audio with precise timestamps indicating when each character was spoken.

Project, 6 operations

create_audio_native_projectCreate audio native projectPOSTCreates an Audio Native project for embedding text-to-speech on webpages.
create_projectCreate projectPOSTCreates a new Studio project for long-form content.
delete_projectDelete projectDELETEDeletes a Studio project and all its content.
get_projectGet projectGETRetrieves details of a Studio project.
list_projectsList projectsGETLists all Studio projects for the user.
stream_project_audioStream project audioPOSTStreams the audio for an entire project snapshot.

Dubbing, 5 operations

delete_dubbing_projectDelete dubbing projectDELETEDeletes a dubbing project and its associated files.
dubbingDubbingPOSTCreates AI-powered dubbing of audio or video content into a different language.
get_dubbed_fileGet dubbed fileGETDownloads the dubbed audio file for a specific language.
get_dubbing_projectGet dubbing projectGETRetrieves status and details of a dubbing project.
list_dubbing_projectsList dubbing projectsGETLists all dubbing projects for the user.

History, 5 operations

delete_history_itemDelete history itemDELETEPermanently deletes a history item and its associated audio file.
download_history_itemsDownload history itemsPOSTDownloads multiple history items as a single zip archive.
get_history_itemGet history itemGETRetrieves details about a specific history item including metadata.
get_history_item_audioGet history item audioGETDownloads the audio file for a specific generation from history without re-generating or consuming credits.
list_historyList historyGETRetrieves paginated history of all text-to-speech generations with metadata and regeneration capabilities.

Agent, 4 operations

create_agentCreate agentPOSTCreates a new conversational AI voice agent for interactive voice applications.
delete_agentDelete agentDELETEDeletes a conversational AI agent.
get_agentGet agentGETRetrieves configuration for a conversational AI agent.
list_agentsList agentsGETLists all conversational AI agents for the user.

Chapter, 3 operations

get_chapterGet chapterGETRetrieves details of a specific chapter.
list_chaptersList chaptersGETLists all chapters in a Studio project.
stream_chapter_audioStream chapter audioPOSTStreams the audio for a specific chapter snapshot.

Dictionary, 3 operations

create_pronunciation_dictionaryCreate pronunciation dictionaryPOSTCreates a new custom pronunciation dictionary from a file.
get_pronunciation_dictionariesGet pronunciation dictionariesGETRetrieves all pronunciation dictionaries available to the user.
get_pronunciation_dictionaryGet pronunciation dictionaryGETRetrieves details of a specific pronunciation dictionary.

Conversation, 2 operations

get_conversationGet conversationGETRetrieves details of a specific agent conversation.
list_conversationsList conversationsGETLists conversations for agents.

Music, 2 operations

compose_musicCompose musicPOSTGenerates a studio-grade music track from a text prompt or structured composition plan using Eleven Music.
stream_musicStream musicPOSTStreams a generated music track for low-latency playback.

Transcription, 2 operations

get_transcriptGet transcriptGETRetrieves a previously created transcription by its ID.
speech_to_textSpeech to textPOSTTranscribes audio or video files to text with high accuracy using the Scribe model.

Model, 1 operation

list_modelsList modelsGETRetrieves all available AI models for text-to-speech and speech-to-speech synthesis with capability information.

Snapshot, 1 operation

list_chapter_snapshotsList chapter snapshotsGETLists all snapshots for a chapter.

Sound, 1 operation

sound_generationSound generationPOSTCreates custom sound effects and audio textures from text descriptions using generative AI.

Subscription, 1 operation

get_user_subscriptionGet user subscriptionGETRetrieves detailed subscription metrics including character usage, limits, reset dates, and plan capabilities.

User, 1 operation

get_userGet userGETFetches authenticated user account information including subscription tier and usage limits.

Use ElevenLabs from Claude Code, Cursor or Codex

Connect ElevenLabs in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its ElevenLabs operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect ElevenLabs

Create your workspace
Sign up free. Nothing to install.
Connect ElevenLabs once
Add your ElevenLabs connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

ElevenLabs integration FAQ

What can you do with the ElevenLabs integration?

LiveContext exposes 60 operations on ElevenLabs, covering voice, audio, project and dubbing. Common uses include Build voice assistants, Check conversion status and Improve clone quality.