Integration · Company data

Connect Claude & ChatGPT to ElevenLabs

Ask your AI to find a voice, read a script aloud or dub a video into another language with ElevenLabs. It can search your voices and the public Voice Library, generate speech, transcribe audio, run dubbing jobs and look through your generation history. It can also read your conversational AI agents and the conversations they have had.

Connect ElevenLabs free

Free plan, no credit card. Takes about a minute.

Try asking

“Find a calm British male voice in the Voice Library and add it to my account.”
The AI searches the public Voice Library by accent, gender and use case and adds the voice you pick under the name you choose.
“Read this product intro aloud with my narrator voice.”
It turns the text into speech with that voice. The audio is saved in your ElevenLabs history, and it uses character credits.
“Dub this video into Spanish: https://example.com/demo.mp4”
It starts a dubbing job from the URL with Spanish as the target language and checks the job until it is done.

What your AI can do

Voices and speech

Search your voices and the public Voice Library, add library voices, adjust voice settings and turn text into speech.

Transcription and dubbing

Transcribe audio or video from a URL, dub files into other languages and fetch dub transcripts as SRT, WebVTT or JSON.

History, agents and usage

Search and clean up your generation history, read agents and their conversations, and check your plan and character usage.

“How many characters do I have left this month?”
It reads your subscription with characters used, characters remaining and the reset date.
“Transcribe this podcast episode and label the speakers.”
It transcribes the audio from the URL with speaker labels switched on.
“Show me yesterday's conversations with our support agent.”
It finds the agent and lists its conversations, then reads the transcript and analysis of any one you open.

23 tools for ElevenLabs

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

add_library_voiceChanges dataAdd a voice from the public Voice Library to your account. Pass `public_user_id`, `voice_id` and the `new_name` to show it under.
create_dubbingChanges dataDub an audio or video file from a `source_url` into another language. Pass `target_lang` and optionally `source_lang`, `name` and `num_speakers`. Uses credits and runs in the background: poll get_dubbing.
delete_history_itemDeletesPermanently delete one item from your generation history by `history_item_id`. This cannot be undone.
get_agentGet one conversational AI agent by `agent_id`, with its prompt, voice and settings.
get_conversationGet one agent conversation by its ID, with the transcript, analysis and metadata.
get_dubbingGet one dubbing job by `dubbing_id`, with its status and target languages.
get_dubbing_transcriptGet the transcript of a finished dub by `dubbing_id` and `language_code`, as `format_type` srt, webvtt or json.
get_history_itemGet one history item by `history_item_id`, with the text, voice, model and date.
get_subscriptionGet the account's subscription: plan, characters used and remaining, and reset date.
get_userGet the connected ElevenLabs user, including character usage and limits. Use to confirm which account you are working in.
get_voiceGet one voice by `voice_id`, with its name, labels, description and settings.
get_voice_settingsGet a voice's settings (stability, similarity boost, style, speed) by `voice_id`.
list_conversationsList conversations your AI agents have had, filtered by `agent_id`, rating or language. Use to find a conversation ID.
list_dubbingsList your dubbing jobs, optionally filtered by status or target language.
list_modelsList the available speech models with their IDs and supported languages. Use to choose a model_id.
search_agentsSearch your conversational AI agents by name with `search`. Use to find an agent_id.
search_historySearch your generation history by `search`, `voice_id`, `model_id` or date range. Use to find earlier generated audio.
search_voice_librarySearch the public ElevenLabs Voice Library by `search`, `language`, `accent`, `gender`, `age` or `use_cases`. Returns voice IDs and public owner IDs.
search_voicesSearch the voices in your account by name with `search`, or filter by `voice_type`, `category`, `language` or `gender`. Use to find a voice_id.
text_to_speechChanges dataTurn `text` into speech with a `voice_id`; optional model_id, language_code and voice_settings. Uses character credits. The audio is saved in your ElevenLabs history (find it with search_history); the audio file itself is not shown in the chat.
transcribe_audioChanges dataTranscribe an audio or video file from a `source_url` into text. Requires `model_id`; optional language_code, diarize (label speakers) and num_speakers.
update_voiceChanges dataRename a voice or change its description and labels by `voice_id`. Requires `name`.
update_voice_settingsChanges dataChange a voice's default settings by `voice_id`: stability, similarity_boost, style, speed or use_speaker_boost.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose ElevenLabs from the app list.
2
Paste your key
Paste an ElevenLabs API key. Open your API keys settings at elevenlabs.io/app/settings/api-keys, click Create API Key, optionally restrict its scopes and credit quota, and copy the key.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in ElevenLabs?

It can read your account, subscription, models, voices, voice settings, generation history, dubbing jobs, agents and agent conversations, and search the public Voice Library. It can turn text into speech, transcribe audio, start dubbing jobs, add library voices, rename voices, change voice settings and delete history items.

Does the AI see my ElevenLabs API key?

No. Your ElevenLabs API key is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on. Text to speech and dubbing use credits, and deleting a history item is permanent, so these can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT, open Settings › Apps & Connectors › Advanced, turn on Developer mode and add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan, and you do not need a credit card to start. Paid plans are billed per completed task. You also need your own ElevenLabs account, so the credits you use are between you and ElevenLabs.

Where does the generated audio end up?

Speech the AI generates is saved in your ElevenLabs history, where you can play and download it. The audio file itself is not shown in the chat. The AI can find earlier audio for you with a history search.