ElevenLabs
ElevenLabs turns text into speech and hosts the voices that speak it — premade, cloned and shared.
Authentication
- API key
Actions
Generic API request. Call any ElevenLabs API endpoint on this connection, for the case where no shipped action covers it yet. The connection supplies the base URL, the authentication and the egress route, so only the path, query and body are yours to fill.
- Get userRetrieve information about the authenticated user / account (GET /user).
- Get user subscriptionRetrieve extended subscription details for the authenticated account (GET /user/subscription).
- Get voiceRetrieve metadata for a single voice by id (GET /voices/{voiceId}).
- List historyList generated-audio history items (GET /history), optionally filtered by page size and voice.
- List modelsList the available models and their capabilities (GET /models).
- List voicesList every voice the connected ElevenLabs account can synthesize with — the shared premade library plus any cloned, generated or professional voices the workspace owns.
- Text to speechSynthesize speech from text with an ElevenLabs voice (POST /text-to-speech/{voiceId}).
- Text to speech (Streaming)Streaming sibling of Text to speech (POST /text-to-speech/{voiceId}/stream/with-timestamps).
Triggers
- Agent call finished (webhook)Starts when an ElevenLabs Agents Platform conversation finishes and its post-call transcription and analysis are ready, delivered by a webhook.
- New generation history itemStarts a workflow when a new text-to-speech generation lands in the ElevenLabs history, filtered server-side by the dateafterunix parameter on the history endpoint.
- Shared voice removal status changed (webhook)Starts when a shared voice the workspace uses is scheduled for removal, has that schedule withdrawn, or is actually removed, delivered by a webhook.
Product names, logos and brands are the property of their respective owners and are used here for identification only. Their use does not imply endorsement by, or affiliation with, those owners.